[ { "model": "dots-3-note", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 3.15, "ci_lo": 2.45, "ci_hi": 3.85, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "dots-3-note", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 23.9, "ci_lo": 20.1, "ci_hi": 27.6, "delta": 20.75, "delta_lo": 16.75, "delta_hi": 24.45, "p_holm": 0.00019998000199980003 }, { "model": "dots-3-note", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 10.35, "ci_lo": 6.45, "ci_hi": 14.95, "delta": 7.199999999999999, "delta_lo": 3.2, "delta_hi": 11.9, "p_holm": 0.00019998000199980003 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 10, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.4, "delta_hi": 0.15, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 10, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.5, "delta": -0.04999999999999999, "delta_lo": -0.35, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 10, "mean_skew": 0.5, "ci_lo": 0.2, "ci_hi": 0.8, "delta": 0.25, "delta_lo": -0.10000000000000003, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 10, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.4, "delta_hi": 0.10000000000000003, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 10, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.4, "delta_hi": 0.15, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 10, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.19999999999999998, "delta_lo": -0.1, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 10, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.1, "delta_lo": -0.25, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 10, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.3, "delta": 0.0, "delta_lo": -0.2, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 10, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.3, "delta": 0.0, "delta_lo": -0.2, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 10, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.19999999999999998, "delta_lo": -0.1, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 10, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 10, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.09999999999999998, "delta_lo": -0.4, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 10, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.6, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 10, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.9, "delta": 0.2, "delta_lo": -0.39999999999999997, "delta_hi": 0.7999999999999999, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 10, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.09999999999999998, "delta_lo": -0.4, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 10, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.09999999999999998, "delta_lo": -0.4, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.75, "ci_lo": 0.55, "ci_hi": 0.9, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 10, "mean_skew": 0.7, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.050000000000000044, "delta_lo": -0.4, "delta_hi": 0.30000000000000004, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 10, "mean_skew": 0.9, "ci_lo": 0.7, "ci_hi": 1.0, "delta": 0.15000000000000002, "delta_lo": -0.1499999999999999, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 10, "mean_skew": 0.9, "ci_lo": 0.7, "ci_hi": 1.0, "delta": 0.15000000000000002, "delta_lo": -0.10000000000000009, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 10, "mean_skew": 0.5, "ci_lo": 0.2, "ci_hi": 0.8, "delta": -0.25, "delta_lo": -0.6000000000000001, "delta_hi": 0.10000000000000009, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 10, "mean_skew": 0.8, "ci_lo": 0.5, "ci_hi": 1.0, "delta": 0.050000000000000044, "delta_lo": -0.30000000000000004, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0P", "n": 10, "mean_skew": 0.6, "ci_lo": 0.3, "ci_hi": 0.9, "delta": -0.15000000000000002, "delta_lo": -0.5, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2P", "n": 10, "mean_skew": 0.8, "ci_lo": 0.5, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.20000000000000007, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.75, "ci_lo": 0.55, "ci_hi": 0.9, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 10, "mean_skew": 0.7, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.050000000000000044, "delta_lo": -0.4, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 10, "mean_skew": 0.7, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.050000000000000044, "delta_lo": -0.4, "delta_hi": 0.30000000000000004, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 10, "mean_skew": 0.6, "ci_lo": 0.3, "ci_hi": 0.9, "delta": -0.15000000000000002, "delta_lo": -0.5, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 10, "mean_skew": 1.0, "ci_lo": 0.7, "ci_hi": 1.3, "delta": 0.25, "delta_lo": -0.09999999999999998, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 10, "mean_skew": 0.8, "ci_lo": 0.5, "ci_hi": 1.0, "delta": 0.050000000000000044, "delta_lo": -0.25, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0P", "n": 10, "mean_skew": 0.5, "ci_lo": 0.2, "ci_hi": 0.8, "delta": -0.25, "delta_lo": -0.6000000000000001, "delta_hi": 0.10000000000000009, "p_holm": 0.44855514448555145 }, { "model": "fable-5.1", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2P", "n": 10, "mean_skew": 0.6, "ci_lo": 0.3, "ci_hi": 0.9, "delta": 0.09999999999999998, "delta_lo": -0.30000000000000004, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.95, "ci_lo": 0.55, "ci_hi": 1.4, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 10, "mean_skew": 1.0, "ci_lo": 0.3, "ci_hi": 1.8, "delta": 0.050000000000000044, "delta_lo": -0.75, "delta_hi": 0.9, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 10, "mean_skew": 0.8, "ci_lo": 0.3, "ci_hi": 1.4, "delta": -0.1499999999999999, "delta_lo": -0.85, "delta_hi": 0.5000000000000001, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 10, "mean_skew": 0.6, "ci_lo": 0.1, "ci_hi": 1.1, "delta": -0.35, "delta_lo": -1.0, "delta_hi": 0.30000000000000004, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 10, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.9, "delta": 0.050000000000000044, "delta_lo": -0.8500000000000001, "delta_hi": 1.05, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 10, "mean_skew": 1.1, "ci_lo": 0.6, "ci_hi": 1.7, "delta": 0.15000000000000013, "delta_lo": -0.5, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0P", "n": 10, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.2, "delta": -0.1499999999999999, "delta_lo": -0.7499999999999999, "delta_hi": 0.4, "p_holm": 0.8293170682931706 }, { "model": "fable-5.1", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2P", "n": 10, "mean_skew": 1.3, "ci_lo": 0.7, "ci_hi": 2.1, "delta": 0.5, "delta_lo": -0.20000000000000007, "delta_hi": 1.3000000000000003, "p_holm": 0.7707229277072293 }, { "model": "gemini", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 8.45, "ci_lo": 6.7, "ci_hi": 10.15, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gemini", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 5.05, "ci_lo": 3.6, "ci_hi": 6.6, "delta": -3.3999999999999995, "delta_lo": -5.65, "delta_hi": -1.0999999999999996, "p_holm": 0.015198480151984802 }, { "model": "gemini", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 10.8, "ci_lo": 7.75, "ci_hi": 14.0, "delta": 2.3500000000000014, "delta_lo": -1.2000000000000002, "delta_hi": 5.949999999999999, "p_holm": 0.22907709229077092 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.2, "p_holm": 0.8429157084291571 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.39999999999999997, "delta_lo": -0.8, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.39999999999999997, "delta_lo": -0.8, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.2, "delta_lo": -0.39999999999999997, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.2, "delta_lo": -0.39999999999999997, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.6, "delta_lo": 0.0, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 1.8, "ci_lo": 0.4, "ci_hi": 3.2, "delta": 1.8, "delta_lo": 0.4, "delta_hi": 3.2, "p_holm": 0.6575342465753424 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 1.8, "ci_lo": 0.8, "ci_hi": 2.8, "delta": 1.8, "delta_lo": 0.8, "delta_hi": 2.8, "p_holm": 0.2524747525247475 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.39999999999999997, "delta_lo": -1.0, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.20000000000000007, "delta_lo": -0.6, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.39999999999999997, "delta_lo": -1.0, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.2, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.6000000000000001, "delta_lo": -0.19999999999999996, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.0, "ci_hi": 1.6, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.6, "delta_lo": 0.0, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.8, "delta_lo": 0.19999999999999996, "delta_hi": 1.4, "p_holm": 0.8794120587941207 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.39999999999999997, "delta_lo": -0.2, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.39999999999999997, "delta_lo": -0.2, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.6, "delta_lo": 0.2, "delta_hi": 1.0, "p_holm": 0.821917808219178 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.0, "delta_lo": -1.2, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 1.4, "ci_lo": 1.0, "ci_hi": 1.8, "delta": 0.3999999999999999, "delta_lo": -0.40000000000000013, "delta_hi": 1.2000000000000002, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 1.8, "ci_lo": 1.4, "ci_hi": 2.0, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.8, "ci_lo": 1.4, "ci_hi": 2.0, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 1.2, "ci_lo": 0.4, "ci_hi": 2.0, "delta": 0.19999999999999996, "delta_lo": -0.9999999999999999, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.2, "delta_lo": -0.4, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.6000000000000001, "delta_lo": -0.19999999999999996, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 1.6, "ci_lo": 0.8, "ci_hi": 2.0, "delta": 1.4000000000000001, "delta_lo": 0.6, "delta_hi": 2.0, "p_holm": 0.2524747525247475 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.6, "delta": 0.3999999999999999, "delta_lo": 0.0, "delta_hi": 0.9999999999999999, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.6000000000000001, "delta_lo": -1.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.6, "delta_lo": 0.2, "delta_hi": 1.0, "p_holm": 0.6575342465753424 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.8, "delta_lo": 0.4, "delta_hi": 1.0, "p_holm": 0.2384761523847615 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.6, "delta_lo": 0.2, "delta_hi": 1.0, "p_holm": 0.6575342465753424 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.6, "delta_lo": 0.2, "delta_hi": 1.0, "p_holm": 0.6575342465753424 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 1.6, "ci_lo": 0.6, "ci_hi": 2.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 1.6, "ci_lo": 0.8, "ci_hi": 2.4, "delta": 0.0, "delta_lo": -1.4000000000000001, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -1.4000000000000001, "delta_lo": -2.6, "delta_hi": -0.3999999999999999, "p_holm": 0.650934906509349 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 1.4, "ci_lo": 0.6, "ci_hi": 2.2, "delta": -0.20000000000000018, "delta_lo": -1.6, "delta_hi": 1.2000000000000002, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 1.2, "ci_lo": 0.2, "ci_hi": 2.2, "delta": -0.40000000000000013, "delta_lo": -1.8000000000000003, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-5.6-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 2.4, "ci_lo": 1.0, "ci_hi": 3.4, "delta": 0.7999999999999998, "delta_lo": -0.8000000000000003, "delta_hi": 2.4, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.6, "delta_lo": 0.2, "delta_hi": 1.0, "p_holm": 0.8344165583441655 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.4, "delta_lo": -0.19999999999999996, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.4, "delta_lo": -0.39999999999999997, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.6, "delta_lo": 0.0, "delta_hi": 1.2000000000000002, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.19999999999999996, "delta_lo": -0.6, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.19999999999999996, "delta_lo": -0.8, "delta_hi": 1.2000000000000002, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.6, "delta": 0.3999999999999999, "delta_lo": -0.3999999999999999, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": -0.20000000000000007, "delta_lo": -1.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.7999999999999999, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": -0.20000000000000007, "delta_lo": -1.2, "delta_hi": 0.7999999999999999, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.2, "delta_lo": -0.39999999999999997, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.39999999999999997, "delta_lo": -0.39999999999999997, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 1.4, "ci_lo": 0.0, "ci_hi": 3.0, "delta": 1.2, "delta_lo": -0.2, "delta_hi": 2.8, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.2, "delta_lo": -0.4, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6-astra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.6, "ci_lo": 0.3, "ci_hi": 0.95, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.65, "ci_lo": 0.35, "ci_hi": 1.0, "delta": 0.050000000000000044, "delta_lo": -0.4, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.7, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.09999999999999998, "delta_lo": -0.35, "delta_hi": 0.55, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 1.15, "ci_lo": 0.8, "ci_hi": 1.5, "delta": 0.5499999999999999, "delta_lo": 0.050000000000000044, "delta_hi": 1.0, "p_holm": 0.261973802619738 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 1.05, "ci_lo": 0.65, "ci_hi": 1.45, "delta": 0.45000000000000007, "delta_lo": -0.050000000000000044, "delta_hi": 0.95, "p_holm": 0.40915908409159085 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 1.05, "ci_lo": 0.75, "ci_hi": 1.35, "delta": 0.45000000000000007, "delta_lo": 0.0, "delta_hi": 0.9, "p_holm": 0.40915908409159085 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.5, "ci_lo": 0.25, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.75, "delta": -0.04999999999999999, "delta_lo": -0.45, "delta_hi": 0.35000000000000003, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.6, "ci_lo": 0.35, "ci_hi": 0.9, "delta": 0.09999999999999998, "delta_lo": -0.30000000000000004, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.65, "ci_lo": 0.35, "ci_hi": 1.0, "delta": 0.15000000000000002, "delta_lo": -0.3, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 1.1, "ci_lo": 0.85, "ci_hi": 1.35, "delta": 0.6000000000000001, "delta_lo": 0.19999999999999996, "delta_hi": 1.0, "p_holm": 0.0664933506649335 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 1.15, "ci_lo": 0.85, "ci_hi": 1.45, "delta": 0.6499999999999999, "delta_lo": 0.2, "delta_hi": 1.05, "p_holm": 0.0664933506649335 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": 0.05, "delta_lo": 0.0, "delta_hi": 0.15, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.9, "ci_lo": 0.7, "ci_hi": 1.1, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 1.05, "ci_lo": 0.75, "ci_hi": 1.35, "delta": 0.15000000000000002, "delta_lo": -0.20000000000000007, "delta_hi": 0.5, "p_holm": 0.5732426757324267 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 1.5, "ci_lo": 1.3, "ci_hi": 1.7, "delta": 0.6, "delta_lo": 0.30000000000000004, "delta_hi": 0.8999999999999999, "p_holm": 0.0059994000599940004 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 1.45, "ci_lo": 1.1, "ci_hi": 1.85, "delta": 0.5499999999999999, "delta_lo": 0.10000000000000009, "delta_hi": 1.0, "p_holm": 0.1103889611038896 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 1.25, "ci_lo": 1.05, "ci_hi": 1.5, "delta": 0.35, "delta_lo": 0.050000000000000044, "delta_hi": 0.6500000000000001, "p_holm": 0.13158684131586842 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 1.65, "ci_lo": 1.4, "ci_hi": 1.95, "delta": 0.7499999999999999, "delta_lo": 0.3999999999999999, "delta_hi": 1.1, "p_holm": 0.0034996500349965005 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0P", "n": 20, "mean_skew": 1.15, "ci_lo": 0.9, "ci_hi": 1.4, "delta": 0.2499999999999999, "delta_lo": -0.050000000000000044, "delta_hi": 0.55, "p_holm": 0.46915308469153083 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2P", "n": 20, "mean_skew": 1.3, "ci_lo": 1.0, "ci_hi": 1.55, "delta": 0.15000000000000013, "delta_lo": -0.20000000000000018, "delta_hi": 0.5, "p_holm": 0.6162383761623837 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 1.05, "ci_lo": 0.9, "ci_hi": 1.2, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 1.15, "ci_lo": 0.9, "ci_hi": 1.4, "delta": 0.09999999999999987, "delta_lo": -0.19999999999999996, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 1.1, "ci_lo": 0.8, "ci_hi": 1.35, "delta": 0.050000000000000044, "delta_lo": -0.29999999999999993, "delta_hi": 0.3500000000000001, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 1.2, "ci_lo": 0.9, "ci_hi": 1.55, "delta": 0.1499999999999999, "delta_lo": -0.20000000000000007, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 1.45, "ci_lo": 1.15, "ci_hi": 1.75, "delta": 0.3999999999999999, "delta_lo": 0.04999999999999982, "delta_hi": 0.75, "p_holm": 0.31396860313968605 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 1.5, "ci_lo": 1.2, "ci_hi": 1.8, "delta": 0.44999999999999996, "delta_lo": 0.10000000000000009, "delta_hi": 0.8, "p_holm": 0.16148385161483853 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0P", "n": 20, "mean_skew": 1.15, "ci_lo": 0.85, "ci_hi": 1.45, "delta": 0.09999999999999987, "delta_lo": -0.20124999999999893, "delta_hi": 0.40000000000000013, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2P", "n": 20, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.45, "delta": 0.050000000000000044, "delta_lo": -0.30000000000000004, "delta_hi": 0.44999999999999996, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.25, "ci_lo": 0.05, "ci_hi": 0.5, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.45, "delta": -0.04999999999999999, "delta_lo": -0.39999999999999997, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.45, "delta": -0.04999999999999999, "delta_lo": -0.35000000000000003, "delta_hi": 0.2512499999999819, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.65, "delta": 0.15000000000000002, "delta_lo": -0.2, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.75, "delta": 0.2, "delta_lo": -0.15000000000000002, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.35, "ci_lo": 0.1, "ci_hi": 0.7, "delta": 0.09999999999999998, "delta_lo": -0.3, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0P", "n": 20, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.04999999999999999, "delta_lo": -0.45, "delta_hi": 0.44999999999999996, "p_holm": 1.0 }, { "model": "gpt-6-luna", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2P", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": -0.1, "delta_lo": -0.5499999999999999, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.4, "delta_lo": -0.20000000000000007, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.2, "p_holm": 0.8474152584741526 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.20000000000000007, "delta_lo": -0.6, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.20000000000000007, "delta_lo": -0.6, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.4, "delta_lo": -1.0, "delta_hi": 0.19999999999999996, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.4, "ci_lo": 1.0, "ci_hi": 1.8, "delta": 0.5999999999999999, "delta_lo": 0.1950000000000045, "delta_hi": 1.2000000000000002, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.0, "delta_lo": -0.6, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 1.4, "ci_lo": 1.0, "ci_hi": 1.8, "delta": 0.3999999999999999, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.6, "delta": 0.19999999999999996, "delta_lo": 0.0, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.8, "delta_lo": -1.4, "delta_hi": -0.2, "p_holm": 0.8089191080891911 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": -0.20000000000000007, "delta_lo": -1.2, "delta_hi": 0.7999999999999999, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": -0.20000000000000007, "delta_lo": -1.2, "delta_hi": 0.7999999999999999, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.4, "delta_lo": -1.2, "delta_hi": 0.39999999999999997, "p_holm": 1.0 }, { "model": "gpt-6-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.7999999999999999, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.55, "delta": 0.15, "delta_lo": -0.1012499999999989, "delta_hi": 0.45, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": 0.19999999999999998, "delta_lo": -0.05000000000000002, "delta_hi": 0.45000000000000007, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": 0.05000000000000002, "delta_lo": -0.19999999999999998, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": 0.1, "delta_lo": -0.15, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.09999999999999999, "delta_lo": -0.3, "delta_hi": 0.05000000000000002, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.55, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.45, "delta_hi": 0.10000000000000003, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": -0.19999999999999998, "delta_lo": -0.5, "delta_hi": 0.05000000000000002, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.45, "delta_hi": 0.10124999999998184, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": -0.19999999999999998, "delta_lo": -0.5, "delta_hi": 0.05000000000000002, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": -0.19999999999999998, "delta_lo": -0.5, "delta_hi": 0.05000000000000002, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.65, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": -0.10000000000000003, "delta_lo": -0.44999999999999996, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.25, "ci_lo": 0.05, "ci_hi": 0.45, "delta": -0.15000000000000002, "delta_lo": -0.45, "delta_hi": 0.15000000000000002, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.5, "ci_lo": 0.3, "ci_hi": 0.7, "delta": 0.09999999999999998, "delta_lo": -0.25, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.25, "delta_lo": -0.55, "delta_hi": 0.04999999999999999, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": -0.050000000000000044, "delta_lo": -0.39999999999999997, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 1.1, "ci_lo": 0.8, "ci_hi": 1.4, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.6, "ci_lo": 0.35, "ci_hi": 0.85, "delta": -0.5000000000000001, "delta_lo": -0.8999999999999999, "delta_hi": -0.09999999999999998, "p_holm": 0.18848115188481152 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.7, "ci_lo": 0.45, "ci_hi": 0.95, "delta": -0.40000000000000013, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 0.38036196380361964 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.85, "ci_lo": 0.5, "ci_hi": 1.2, "delta": -0.2500000000000001, "delta_lo": -0.7000000000000001, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.9, "ci_lo": 0.65, "ci_hi": 1.15, "delta": -0.20000000000000007, "delta_lo": -0.6, "delta_hi": 0.19999999999999996, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 1.0, "ci_lo": 0.7, "ci_hi": 1.3, "delta": -0.10000000000000009, "delta_lo": -0.5499999999999999, "delta_hi": 0.30000000000000004, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0P", "n": 20, "mean_skew": 0.7, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.40000000000000013, "delta_lo": -0.85, "delta_hi": 0.050000000000000044, "p_holm": 0.27417258274172585 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2P", "n": 20, "mean_skew": 0.8, "ci_lo": 0.55, "ci_hi": 1.05, "delta": 0.10000000000000009, "delta_lo": -0.30000000000000004, "delta_hi": 0.5, "p_holm": 0.8158184181581842 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.85, "ci_lo": 0.6, "ci_hi": 1.1, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.8, "ci_lo": 0.55, "ci_hi": 1.05, "delta": -0.04999999999999993, "delta_lo": -0.4, "delta_hi": 0.30000000000000004, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.9, "ci_lo": 0.6, "ci_hi": 1.2, "delta": 0.050000000000000044, "delta_lo": -0.35, "delta_hi": 0.44999999999999996, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.75, "ci_lo": 0.5, "ci_hi": 1.05, "delta": -0.09999999999999998, "delta_lo": -0.45000000000000007, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 1.0, "ci_lo": 0.75, "ci_hi": 1.25, "delta": 0.15000000000000002, "delta_lo": -0.19999999999999996, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.9, "ci_lo": 0.7, "ci_hi": 1.1, "delta": 0.050000000000000044, "delta_lo": -0.2500000000000001, "delta_hi": 0.3500000000000001, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0P", "n": 20, "mean_skew": 0.95, "ci_lo": 0.65, "ci_hi": 1.25, "delta": 0.09999999999999998, "delta_lo": -0.29999999999999993, "delta_hi": 0.4999999999999999, "p_holm": 0.8025197480251974 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2P", "n": 20, "mean_skew": 0.65, "ci_lo": 0.4, "ci_hi": 0.9, "delta": -0.29999999999999993, "delta_lo": -0.7, "delta_hi": 0.050000000000000044, "p_holm": 0.43075692430756923 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.75, "ci_lo": 0.45, "ci_hi": 1.1, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.6, "ci_lo": 0.35, "ci_hi": 0.85, "delta": -0.15000000000000002, "delta_lo": -0.6, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.7, "delta": -0.3, "delta_lo": -0.7000000000000001, "delta_hi": 0.10000000000000003, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.95, "ci_lo": 0.65, "ci_hi": 1.25, "delta": 0.19999999999999996, "delta_lo": -0.2500000000000001, "delta_hi": 0.65, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.4, "ci_lo": 0.2, "ci_hi": 0.6, "delta": -0.35, "delta_lo": -0.75, "delta_hi": 0.04999999999999993, "p_holm": 0.8134186581341867 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.65, "ci_lo": 0.35, "ci_hi": 1.0, "delta": -0.09999999999999998, "delta_lo": -0.55, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0P", "n": 20, "mean_skew": 0.6, "ci_lo": 0.3, "ci_hi": 0.9, "delta": -0.15000000000000002, "delta_lo": -0.6000000000000001, "delta_hi": 0.29999999999999993, "p_holm": 1.0 }, { "model": "gpt-6.1-sol", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2P", "n": 20, "mean_skew": 0.75, "ci_lo": 0.5, "ci_hi": 1.0, "delta": 0.15000000000000002, "delta_lo": -0.25, "delta_hi": 0.55, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.4, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.2, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": -0.4, "delta_lo": -1.0, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 1.4, "ci_lo": 0.6, "ci_hi": 2.2, "delta": 0.3999999999999999, "delta_lo": -0.6, "delta_hi": 1.4000000000000001, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 1.2, "ci_lo": 0.6, "ci_hi": 1.8, "delta": 0.19999999999999996, "delta_lo": -0.6000000000000001, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.6, "delta": 0.19999999999999996, "delta_lo": -0.40000000000000013, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.0, "delta_lo": -0.7999999999999999, "delta_hi": 0.7999999999999999, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.0, "ci_hi": 2.0, "delta": -0.19999999999999996, "delta_lo": -1.0, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": -0.19999999999999996, "delta_lo": -0.8, "delta_hi": 0.3999999999999999, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.19999999999999996, "p_holm": 0.8249175082491751 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.6000000000000001, "delta_lo": -0.19999999999999996, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.0, "ci_hi": 2.6, "delta": 0.8, "delta_lo": -0.39999999999999997, "delta_hi": 2.4, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.8, "delta_lo": 0.4, "delta_hi": 1.0, "p_holm": 0.22747725227477253 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.6000000000000001, "delta_lo": -0.19999999999999996, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "gpt-6.1-terra", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.8, "delta_lo": 0.19999999999999996, "delta_hi": 1.4000000000000001, "p_holm": 0.6527347265273473 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.75, "ci_lo": 0.5, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": -0.4, "delta_lo": -0.75, "delta_hi": -0.04999999999999999, "p_holm": 0.30496950304969506 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.4, "ci_lo": 0.2, "ci_hi": 0.6, "delta": -0.35, "delta_lo": -0.7, "delta_hi": 0.0, "p_holm": 0.43515648435156484 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.5, "ci_lo": 0.3, "ci_hi": 0.7, "delta": -0.25, "delta_lo": -0.6000000000000001, "delta_hi": 0.09999999999999998, "p_holm": 0.6140385961403859 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.55, "ci_lo": 0.35, "ci_hi": 0.75, "delta": -0.19999999999999996, "delta_lo": -0.55, "delta_hi": 0.15000000000000002, "p_holm": 0.6140385961403859 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.7, "delta": -0.3, "delta_lo": -0.7, "delta_hi": 0.09999999999999998, "p_holm": 0.6140385961403859 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": -0.04999999999999999, "delta_lo": -0.35, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.35, "ci_lo": 0.1, "ci_hi": 0.6, "delta": 0.0, "delta_lo": -0.30000000000000004, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.5, "ci_lo": 0.3, "ci_hi": 0.7, "delta": 0.15000000000000002, "delta_lo": -0.15000000000000002, "delta_hi": 0.45, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": -0.04999999999999999, "delta_lo": -0.35, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": -0.09999999999999998, "delta_lo": -0.39999999999999997, "delta_hi": 0.19999999999999998, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.5, "ci_lo": 0.2, "ci_hi": 0.85, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": -0.2, "delta_lo": -0.6000000000000001, "delta_hi": 0.15000000000000002, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.75, "delta": -0.04999999999999999, "delta_lo": -0.5, "delta_hi": 0.39999999999999997, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.4, "ci_lo": 0.2, "ci_hi": 0.6, "delta": -0.09999999999999998, "delta_lo": -0.5499999999999999, "delta_hi": 0.25000000000000006, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": -0.3, "delta_lo": -0.7, "delta_hi": 0.04999999999999999, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.7, "delta": -0.2, "delta_lo": -0.7, "delta_hi": 0.29999999999999993, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.8, "ci_lo": 0.5, "ci_hi": 1.1, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.7, "delta": -0.35000000000000003, "delta_lo": -0.75, "delta_hi": 0.04999999999999999, "p_holm": 0.4724527547245276 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.65, "ci_lo": 0.4, "ci_hi": 0.95, "delta": -0.15000000000000002, "delta_lo": -0.55, "delta_hi": 0.25, "p_holm": 0.651034896510349 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.7, "delta": -0.35000000000000003, "delta_lo": -0.75, "delta_hi": 0.050000000000000044, "p_holm": 0.4724527547245276 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.35, "ci_lo": 0.1, "ci_hi": 0.6, "delta": -0.45000000000000007, "delta_lo": -0.85, "delta_hi": -0.050000000000000044, "p_holm": 0.292970702929707 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.65, "delta": -0.4, "delta_lo": -0.7999999999999999, "delta_hi": 0.0, "p_holm": 0.385961403859614 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0P", "n": 20, "mean_skew": 0.5, "ci_lo": 0.25, "ci_hi": 0.8, "delta": -0.30000000000000004, "delta_lo": -0.7000000000000001, "delta_hi": 0.10000000000000009, "p_holm": 0.5211478852114788 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2P", "n": 20, "mean_skew": 0.55, "ci_lo": 0.25, "ci_hi": 0.85, "delta": 0.050000000000000044, "delta_lo": -0.35000000000000003, "delta_hi": 0.45, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.75, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.7, "delta": -0.04999999999999999, "delta_lo": -0.45, "delta_hi": 0.35000000000000003, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.5, "ci_lo": 0.25, "ci_hi": 0.75, "delta": 0.04999999999999999, "delta_lo": -0.35, "delta_hi": 0.44999999999999996, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.75, "ci_lo": 0.45, "ci_hi": 1.05, "delta": 0.3, "delta_lo": -0.1499999999999999, "delta_hi": 0.7000000000000001, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.65, "delta": -0.04999999999999999, "delta_lo": -0.44999999999999996, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": -0.10000000000000003, "delta_lo": -0.45000000000000007, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0P", "n": 20, "mean_skew": 0.75, "ci_lo": 0.4, "ci_hi": 1.1, "delta": 0.3, "delta_lo": -0.15000000000000002, "delta_hi": 0.75, "p_holm": 0.28147185281471854 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2P", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.4, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.2, "p_holm": 0.026797320267973202 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 19, "mean_skew": 0.15789473684210525, "ci_lo": 0.0, "ci_hi": 0.42105263157894735, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": -0.05789473684210525, "delta_lo": -0.32105263157894737, "delta_hi": 0.15, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.5, "delta": 0.04210526315789476, "delta_lo": -0.3157894736842105, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.15789473684210525, "delta_lo": -0.42105263157894735, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.4, "delta": -0.00789473684210526, "delta_lo": -0.31842105263157894, "delta_hi": 0.29736842105263156, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.3, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.14210526315789473, "delta_lo": -0.22105263157894733, "delta_hi": 0.5421052631578946, "p_holm": 1.0 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0P", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.15789473684210525, "delta_lo": -0.42105263157894735, "delta_hi": 0.0, "p_holm": 0.4667533246675332 }, { "model": "haiku-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2P", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": 0.15, "delta_lo": 0.0, "delta_hi": 0.3, "p_holm": 0.4667533246675332 }, { "model": "nemotron-3-ultra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 3.3, "ci_lo": 2.0, "ci_hi": 4.7, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "nemotron-3-ultra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 2.55, "ci_lo": 1.65, "ci_hi": 3.65, "delta": -0.75, "delta_lo": -2.45, "delta_hi": 0.9000000000000004, "p_holm": 0.44175582441755823 }, { "model": "nemotron-3-ultra", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 5.95, "ci_lo": 3.95, "ci_hi": 8.05, "delta": 2.6500000000000004, "delta_lo": 0.25, "delta_hi": 5.1, "p_holm": 0.0993900609939006 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.6000000000000001, "delta_lo": 0.0, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.2, "ci_hi": 1.4, "delta": 0.6000000000000001, "delta_lo": -0.19999999999999996, "delta_hi": 1.4, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.39999999999999997, "delta_lo": -0.2, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.2, "delta_lo": -0.39999999999999997, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.39999999999999997, "delta_lo": -0.39999999999999997, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -1.0, "delta_hi": 0.4, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": -0.6000000000000001, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.19999999999999996, "delta_lo": -0.8, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 2.0, "ci_lo": 0.8, "ci_hi": 3.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 1.8, "ci_lo": 1.0, "ci_hi": 2.6, "delta": -0.19999999999999996, "delta_lo": -2.0, "delta_hi": 1.4000000000000001, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 1.4, "ci_lo": 0.6, "ci_hi": 2.2, "delta": -0.6000000000000001, "delta_lo": -2.4, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 2.2, "ci_lo": 1.6, "ci_hi": 2.8, "delta": 0.20000000000000018, "delta_lo": -1.5999999999999996, "delta_hi": 1.6, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 1.6, "ci_lo": 0.8, "ci_hi": 2.0, "delta": -0.3999999999999999, "delta_lo": -2.1999999999999997, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 2.2, "ci_lo": 1.0, "ci_hi": 3.2, "delta": 0.20000000000000018, "delta_lo": -1.7999999999999998, "delta_hi": 1.9999999999999998, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.4, "delta_lo": -0.20000000000000007, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 1.0, "ci_lo": 0.4, "ci_hi": 1.6, "delta": 0.4, "delta_lo": -0.20000000000000007, "delta_hi": 1.2, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 1.0, "ci_lo": 1.0, "ci_hi": 1.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 1.4, "ci_lo": 1.0, "ci_hi": 1.8, "delta": 0.3999999999999999, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.19999999999999996, "p_holm": 0.821917808219178 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.19999999999999996, "delta_lo": -0.6, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.6, "delta_lo": -1.0, "delta_hi": -0.19999999999999996, "p_holm": 0.821917808219178 }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 2.8, "ci_lo": 1.8, "ci_hi": 4.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 1.6, "ci_lo": 1.2, "ci_hi": 2.0, "delta": -1.1999999999999997, "delta_lo": -2.4000000000000004, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 2.2, "ci_lo": 1.4, "ci_hi": 3.0, "delta": -0.5999999999999996, "delta_lo": -2.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 2.2, "ci_lo": 1.6, "ci_hi": 2.8, "delta": -0.5999999999999996, "delta_lo": -2.0, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 2.0, "ci_lo": 0.8, "ci_hi": 3.0, "delta": -0.7999999999999998, "delta_lo": -2.4000000000000004, "delta_hi": 0.7999999999999998, "p_holm": 1.0 }, { "model": "opus-4.8", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 3.6, "ci_lo": 3.0, "ci_hi": 4.4, "delta": 0.8000000000000003, "delta_lo": -0.6000000000000001, "delta_hi": 2.2, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": 0.09999999999999999, "delta_lo": -0.05000000000000002, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": 0.15000000000000002, "delta_lo": -0.05, "delta_hi": 0.35, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": 0.0, "delta_lo": -0.15, "delta_hi": 0.15, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": 0.15000000000000002, "delta_lo": -0.05, "delta_hi": 0.35000000000000003, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": 0.15000000000000002, "delta_lo": -0.05, "delta_hi": 0.35000000000000003, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.1, "ci_lo": 0.0, "ci_hi": 0.25, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.1, "delta_lo": -0.25, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.05, "delta_lo": -0.2, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.05, "delta_lo": -0.2, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.05, "delta_lo": -0.2, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.05, "delta_lo": -0.2, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 0.45, "ci_lo": 0.2, "ci_hi": 0.7, "delta": 0.2, "delta_lo": -0.10000000000000003, "delta_hi": 0.5499999999999999, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 0.7, "ci_lo": 0.35, "ci_hi": 1.1, "delta": 0.44999999999999996, "delta_lo": 0.04999999999999999, "delta_hi": 0.8500000000000001, "p_holm": 0.37396260373962603 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 0.4, "ci_lo": 0.15, "ci_hi": 0.7, "delta": 0.15000000000000002, "delta_lo": -0.19999999999999998, "delta_hi": 0.5, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 0.35, "ci_lo": 0.1, "ci_hi": 0.65, "delta": 0.09999999999999998, "delta_lo": -0.24999999999999997, "delta_hi": 0.45000000000000007, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 0.6, "ci_lo": 0.25, "ci_hi": 1.0, "delta": 0.35, "delta_lo": -0.04999999999999999, "delta_hi": 0.7999999999999999, "p_holm": 0.7615238476152385 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 0.25, "ci_lo": 0.05, "ci_hi": 0.45, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": -0.04999999999999999, "delta_lo": -0.30000000000000004, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": -0.04999999999999999, "delta_lo": -0.30000000000000004, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 20, "mean_skew": 0.35, "ci_lo": 0.15, "ci_hi": 0.55, "delta": 0.09999999999999998, "delta_lo": -0.19999999999999998, "delta_hi": 0.39999999999999997, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 20, "mean_skew": 0.2, "ci_lo": 0.05, "ci_hi": 0.4, "delta": -0.04999999999999999, "delta_lo": -0.30000000000000004, "delta_hi": 0.2, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 0.5, "ci_lo": 0.25, "ci_hi": 0.75, "delta": 0.25, "delta_lo": -0.050000000000000044, "delta_hi": 0.55, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0P", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": 0.0, "delta_lo": -0.25, "delta_hi": 0.25, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2P", "n": 20, "mean_skew": 0.05, "ci_lo": 0.0, "ci_hi": 0.15, "delta": -0.2, "delta_lo": -0.4, "delta_hi": 0.0, "p_holm": 0.3645635436456354 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.4, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": -0.04999999999999999, "delta_lo": -0.30000000000000004, "delta_hi": 0.20000000000000007, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": 0.0, "delta_lo": -0.3, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": 0.0, "delta_lo": -0.3, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 20, "mean_skew": 0.15, "ci_lo": 0.0, "ci_hi": 0.3, "delta": -0.15, "delta_lo": -0.4, "delta_hi": 0.1, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0P", "n": 20, "mean_skew": 0.3, "ci_lo": 0.1, "ci_hi": 0.5, "delta": 0.0, "delta_lo": -0.3, "delta_hi": 0.3, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2P", "n": 20, "mean_skew": 0.25, "ci_lo": 0.1, "ci_hi": 0.45, "delta": -0.04999999999999999, "delta_lo": -0.30000000000000004, "delta_hi": 0.24999999999999997, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 20, "mean_skew": 1.25, "ci_lo": 0.8, "ci_hi": 1.75, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 20, "mean_skew": 1.7, "ci_lo": 1.1, "ci_hi": 2.3, "delta": 0.44999999999999996, "delta_lo": -0.30000000000000004, "delta_hi": 1.2000000000000002, "p_holm": 0.9767023297670233 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 20, "mean_skew": 2.35, "ci_lo": 1.8, "ci_hi": 2.85, "delta": 1.1, "delta_lo": 0.3999999999999999, "delta_hi": 1.8, "p_holm": 0.041995800419958006 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 20, "mean_skew": 1.75, "ci_lo": 1.4, "ci_hi": 2.15, "delta": 0.5, "delta_lo": -0.10000000000000009, "delta_hi": 1.1, "p_holm": 0.6587341265873413 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 20, "mean_skew": 1.45, "ci_lo": 0.9, "ci_hi": 2.0, "delta": 0.19999999999999996, "delta_lo": -0.5499999999999999, "delta_hi": 0.95, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 20, "mean_skew": 1.5, "ci_lo": 1.1, "ci_hi": 1.95, "delta": 0.25, "delta_lo": -0.3999999999999999, "delta_hi": 0.8999999999999999, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0P", "n": 20, "mean_skew": 1.4, "ci_lo": 0.8, "ci_hi": 2.05, "delta": 0.1499999999999999, "delta_lo": -0.6499999999999999, "delta_hi": 0.95, "p_holm": 1.0 }, { "model": "opus-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2P", "n": 20, "mean_skew": 1.45, "ci_lo": 1.0, "ci_hi": 1.9, "delta": 0.050000000000000044, "delta_lo": -0.75, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -0.4, "delta_lo": -0.8, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.19999999999999996, "delta_lo": -0.4, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 1.2, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.39999999999999997, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.0, "delta_lo": -0.6000000000000001, "delta_hi": 0.6000000000000001, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": -0.2, "delta_lo": -0.8, "delta_hi": 0.39999999999999997, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": 0.4, "delta_lo": 0.0, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": 0.0, "delta_lo": 0.0, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "CHECKLIST", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": 0.2, "delta_lo": 0.0, "delta_hi": 0.6, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.0, "ci_hi": 1.4, "delta": 0.0, "delta_lo": -1.0, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B1", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": 0.20000000000000007, "delta_lo": -0.6, "delta_hi": 1.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.0, "delta_lo": -0.8, "delta_hi": 0.8, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "C0", "n": 5, "mean_skew": 1.2, "ci_lo": 1.0, "ci_hi": 1.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A1", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.7999999999999999, "delta_lo": -1.4, "delta_hi": -0.19999999999999996, "p_holm": 0.46595340465953405 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "A2", "n": 5, "mean_skew": 0.0, "ci_lo": 0.0, "ci_hi": 0.0, "delta": -1.2, "delta_lo": -1.6, "delta_hi": -1.0, "p_holm": 0.033996600339966 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B1", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.3999999999999999, "delta_lo": -0.9999999999999999, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B2", "n": 5, "mean_skew": 0.8, "ci_lo": 0.4, "ci_hi": 1.0, "delta": -0.3999999999999999, "delta_lo": -0.9999999999999999, "delta_hi": 0.0, "p_holm": 1.0 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "GUARD_ON", "condition": "B3", "n": 5, "mean_skew": 0.4, "ci_lo": 0.0, "ci_hi": 0.8, "delta": -0.7999999999999999, "delta_lo": -1.4, "delta_hi": -0.19999999999999996, "p_holm": 0.46595340465953405 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "C0", "n": 5, "mean_skew": 0.2, "ci_lo": 0.0, "ci_hi": 0.6, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A1", "n": 5, "mean_skew": 1.0, "ci_lo": 0.2, "ci_hi": 1.8, "delta": 0.8, "delta_lo": 0.0, "delta_hi": 1.6, "p_holm": 0.8441155884411559 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "A2", "n": 5, "mean_skew": 0.6, "ci_lo": 0.2, "ci_hi": 1.0, "delta": 0.39999999999999997, "delta_lo": -0.2, "delta_hi": 1.0, "p_holm": 0.8441155884411559 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B1", "n": 5, "mean_skew": 1.4, "ci_lo": 0.6, "ci_hi": 2.0, "delta": 1.2, "delta_lo": 0.39999999999999997, "delta_hi": 2.0, "p_holm": 0.3575642435756424 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B2", "n": 5, "mean_skew": 2.4, "ci_lo": 2.0, "ci_hi": 2.8, "delta": 2.1999999999999997, "delta_lo": 1.6, "delta_hi": 2.8, "p_holm": 0.033996600339966 }, { "model": "sonnet-5.5", "task": "OPEN", "guard": "NO_PLAYBOOK", "condition": "B3", "n": 5, "mean_skew": 1.4, "ci_lo": 0.2, "ci_hi": 3.2, "delta": 1.2, "delta_lo": -0.19999999999999996, "delta_hi": 3.0, "p_holm": 0.8441155884411559 }, { "model": "xing-4.0", "task": "OPEN", "guard": "GUARD_OFF", "condition": "C0", "n": 20, "mean_skew": 13.1, "ci_lo": 8.5, "ci_hi": 17.8, "delta": null, "delta_lo": null, "delta_hi": null, "p_holm": null }, { "model": "xing-4.0", "task": "OPEN", "guard": "GUARD_OFF", "condition": "A2", "n": 20, "mean_skew": 11.8, "ci_lo": 8.2, "ci_hi": 15.7, "delta": -1.299999999999999, "delta_lo": -7.4, "delta_hi": 4.65, "p_holm": 1.0 }, { "model": "xing-4.0", "task": "OPEN", "guard": "GUARD_OFF", "condition": "B3", "n": 20, "mean_skew": 11.1, "ci_lo": 6.65, "ci_hi": 16.15, "delta": -2.0, "delta_lo": -8.799999999999999, "delta_hi": 4.751249999999982, "p_holm": 1.0 } ]