{ "generated": "2026-04-19T10:56:50.302405", "benchmark_id": "combined", "models": [ { "id": "claude-sonnet-4-6", "provider": "anthropic", "label": "Claude Sonnet 4.6" }, { "id": "deepseek-chat", "provider": "deepseek", "label": "DeepSeek" }, { "id": "gemini-2.5-flash", "provider": "google", "label": "Gemini 2.5 Flash" }, { "id": "gpt-5.4", "provider": "openai", "label": "GPT-5.4" }, { "id": "gpt-5.4-mini", "provider": "openai", "label": "GPT-5.4 Mini" }, { "id": "qwen-2.5-72b-instruct", "provider": "qwen", "label": "Qwen 2.5 72b Instruct" } ], "modes": [ { "id": "stub", "label": "Baseline (A)" }, { "id": "reasoning", "label": "Prompted (B)" }, { "id": "light_hints", "label": "Knowledge (C)" }, { "id": "planner", "label": "Planner (D)" } ], "quests": [ { "id": "Badday_eng", "lang": "EN" }, { "id": "Banket_eng", "lang": "EN" }, { "id": "Boat", "lang": "EN" }, { "id": "Codebox_eng", "lang": "EN" }, { "id": "Depth_eng", "lang": "EN" }, { "id": "Driver_eng", "lang": "EN" }, { "id": "Edelweiss_eng", "lang": "EN" }, { "id": "Election_eng", "lang": "EN" }, { "id": "Foncers_eng", "lang": "EN" }, { "id": "Leonardo_eng", "lang": "EN" }, { "id": "Ministry_eng", "lang": "EN" }, { "id": "Pizza_eng", "lang": "EN" }, { "id": "Prison_eng", "lang": "EN" }, { "id": "Robots_eng", "lang": "EN" }, { "id": "Ski_eng", "lang": "EN" } ], "results": [ { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 26.0, "avg_tokens": 16641.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7692307692307693 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 32509.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7142857142857143 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15640.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 6.0, "avg_tokens": 4424.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 69.0, "avg_tokens": 52455.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6521739130434783 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 157.0, "avg_tokens": 117594.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7452229299363057 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 42.0, "avg_tokens": 24618.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6904761904761905 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 74.0, "avg_tokens": 70017.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7027027027027027 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 20449.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5806451612903226 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 104.0, "avg_tokens": 70821.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7403846153846154 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 112.0, "avg_tokens": 70587.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6339285714285714 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 26.0, "avg_tokens": 19114.0, "avg_cost_usd": 0.0, "repetition_rate": 0.4230769230769231 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 91.0, "avg_tokens": 61528.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8351648351648352 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 74.0, "avg_tokens": 45617.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8783783783783784 }, { "model": "claude-sonnet-4-6", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 57.0, "avg_tokens": 47297.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7543859649122807 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 27.0, "avg_tokens": 21892.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 37810.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7058823529411765 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 16.0, "avg_tokens": 16347.0, "avg_cost_usd": 0.0, "repetition_rate": 0.875 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 6.0, "avg_tokens": 5388.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 28854.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6451612903225806 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 53.0, "avg_tokens": 47450.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7358490566037735 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 22884.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 72.0, "avg_tokens": 81639.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6388888888888888 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 22960.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7037037037037037 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 107.0, "avg_tokens": 92679.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7476635514018691 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 66.0, "avg_tokens": 50960.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8939393939393939 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 31095.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5294117647058824 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 58.0, "avg_tokens": 48779.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8103448275862069 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 80.0, "avg_tokens": 63624.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8375 }, { "model": "claude-sonnet-4-6", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 64.0, "avg_tokens": 64862.0, "avg_cost_usd": 0.0, "repetition_rate": 0.703125 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 26.0, "avg_tokens": 21626.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8076923076923077 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 37380.0, "avg_cost_usd": 0.0, "repetition_rate": 0.696969696969697 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 19617.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 6.0, "avg_tokens": 5582.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 40.0, "avg_tokens": 38330.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 11.0, "avg_tokens": 9509.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7272727272727273 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 23949.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7741935483870968 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 67.0, "avg_tokens": 76668.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6865671641791045 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 30.0, "avg_tokens": 26132.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 110.0, "avg_tokens": 96912.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7454545454545455 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 173.0, "avg_tokens": 140415.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7109826589595376 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 28.0, "avg_tokens": 26283.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5357142857142857 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 113.0, "avg_tokens": 99256.0, "avg_cost_usd": 0.0, "repetition_rate": 0.831858407079646 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 114.0, "avg_tokens": 92708.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8070175438596491 }, { "model": "claude-sonnet-4-6", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 80.0, "avg_tokens": 82368.0, "avg_cost_usd": 0.0, "repetition_rate": 0.725 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 26.0, "avg_tokens": 35741.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7692307692307693 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 52148.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 20.0, "avg_tokens": 29732.0, "avg_cost_usd": 0.0, "repetition_rate": 0.9 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 26.0, "avg_tokens": 37501.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8076923076923077 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 46264.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5588235294117647 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 63.0, "avg_tokens": 81533.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 20.0, "avg_tokens": 24305.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 56.0, "avg_tokens": 113607.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6607142857142857 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 36117.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 86.0, "avg_tokens": 97188.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7674418604651163 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 66.0, "avg_tokens": 80552.0, "avg_cost_usd": 0.0, "repetition_rate": 0.9090909090909091 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 29.0, "avg_tokens": 48239.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5517241379310345 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 37280.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8709677419354839 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 29.0, "avg_tokens": 35299.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8620689655172413 }, { "model": "claude-sonnet-4-6", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 50.0, "avg_tokens": 67707.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 47.0, "avg_tokens": 27847.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7021276595744681 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 24.0, "avg_tokens": 18613.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 14.0, "avg_tokens": 9263.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7857142857142857 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 24917.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 37.0, "avg_tokens": 24038.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6216216216216216 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 11.0, "avg_tokens": 6524.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7272727272727273 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 46.0, "avg_tokens": 25258.0, "avg_cost_usd": 0.0, "repetition_rate": 0.782608695652174 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 3.0, "avg_tokens": 1708.0, "avg_cost_usd": 0.0, "repetition_rate": 0.3333333333333333 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 23.0, "avg_tokens": 13790.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6521739130434783 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 97.0, "avg_tokens": 58068.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7731958762886598 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 192.0, "avg_tokens": 105252.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7604166666666666 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 26.0, "avg_tokens": 16582.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5769230769230769 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 112.0, "avg_tokens": 66828.0, "avg_cost_usd": 0.0, "repetition_rate": 0.875 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 59.0, "avg_tokens": 31440.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8305084745762712 }, { "model": "deepseek-chat", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 54.0, "avg_tokens": 39869.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5925925925925926 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 29.0, "avg_tokens": 20484.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8275862068965517 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 31974.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6176470588235294 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15113.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 13.0, "avg_tokens": 11452.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6153846153846154 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 26968.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6363636363636364 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 14.0, "avg_tokens": 10216.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7857142857142857 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 44.0, "avg_tokens": 28649.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7954545454545454 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 87.0, "avg_tokens": 88152.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7471264367816092 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 20137.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6296296296296297 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 114.0, "avg_tokens": 85280.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7719298245614035 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 24781.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8055555555555556 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 37.0, "avg_tokens": 28864.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5675675675675675 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 212.0, "avg_tokens": 162505.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8113207547169812 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 18552.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "deepseek-chat", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 99.0, "avg_tokens": 87991.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6363636363636364 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 28.0, "avg_tokens": 20553.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8214285714285714 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 23478.0, "avg_cost_usd": 0.0, "repetition_rate": 0.72 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15375.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 19.0, "avg_tokens": 17803.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7368421052631579 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 26003.0, "avg_cost_usd": 0.0, "repetition_rate": 0.59375 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 26552.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7941176470588235 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 22903.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8387096774193549 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 58.0, "avg_tokens": 58206.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7068965517241379 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 37.0, "avg_tokens": 28454.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6756756756756757 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 116.0, "avg_tokens": 88347.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7413793103448276 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 103.0, "avg_tokens": 70990.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8640776699029126 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 23.0, "avg_tokens": 18276.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5652173913043478 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 201.0, "avg_tokens": 160860.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8507462686567164 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 46.0, "avg_tokens": 31775.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8478260869565217 }, { "model": "deepseek-chat", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 83.0, "avg_tokens": 75220.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7108433734939759 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 28.0, "avg_tokens": 28636.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8214285714285714 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 48068.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6363636363636364 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 18163.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7368421052631579 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 16.0, "avg_tokens": 17939.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 110.0, "avg_tokens": 104536.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6909090909090909 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 11.0, "avg_tokens": 12383.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7272727272727273 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 74.0, "avg_tokens": 62211.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7297297297297297 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 47.0, "avg_tokens": 72984.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7659574468085106 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 28320.0, "avg_cost_usd": 0.0, "repetition_rate": 0.78125 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 115.0, "avg_tokens": 86425.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7739130434782608 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 74.0, "avg_tokens": 71040.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8783783783783784 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 18.0, "avg_tokens": 21103.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 113.0, "avg_tokens": 97851.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8495575221238938 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 27414.0, "avg_cost_usd": 0.0, "repetition_rate": 0.71875 }, { "model": "deepseek-chat", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 101.0, "avg_tokens": 121008.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6831683168316832 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 19112.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8484848484848485 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 26.0, "avg_tokens": 20963.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5769230769230769 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 11944.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7368421052631579 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 25719.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7741935483870968 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 25243.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6944444444444444 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 69.0, "avg_tokens": 45808.0, "avg_cost_usd": 0.0, "repetition_rate": 0.782608695652174 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 59.0, "avg_tokens": 33160.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7796610169491526 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 44.0, "avg_tokens": 38756.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7045454545454546 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 18749.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5806451612903226 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 81.0, "avg_tokens": 51006.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7530864197530864 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 122.0, "avg_tokens": 70141.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7540983606557377 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 19951.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6129032258064516 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 325.0, "avg_tokens": 205555.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8307692307692308 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 40.0, "avg_tokens": 22092.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "gemini-2.5-flash", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 59.0, "avg_tokens": 48676.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6779661016949152 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 30.0, "avg_tokens": 22720.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 32571.0, "avg_cost_usd": 0.0, "repetition_rate": 0.696969696969697 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15250.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6842105263157895 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 14.0, "avg_tokens": 13190.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6428571428571429 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 27518.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6875 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 78.0, "avg_tokens": 65540.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8076923076923077 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 24116.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 68.0, "avg_tokens": 72534.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7352941176470589 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 30.0, "avg_tokens": 23512.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 112.0, "avg_tokens": 89509.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7767857142857143 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 149.0, "avg_tokens": 111612.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7315436241610739 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 45.0, "avg_tokens": 37388.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5555555555555556 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 330.0, "avg_tokens": 272571.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8272727272727273 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 109.0, "avg_tokens": 80020.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8440366972477065 }, { "model": "gemini-2.5-flash", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 50.0, "avg_tokens": 49160.0, "avg_cost_usd": 0.0, "repetition_rate": 0.66 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 30.0, "avg_tokens": 23045.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8333333333333334 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 22.0, "avg_tokens": 21621.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6818181818181818 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15604.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 31749.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 31234.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6571428571428571 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 94.0, "avg_tokens": 80831.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8085106382978723 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 25348.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6764705882352942 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 65.0, "avg_tokens": 70820.0, "avg_cost_usd": 0.0, "repetition_rate": 0.676923076923077 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 23997.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6451612903225806 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 108.0, "avg_tokens": 88061.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8055555555555556 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 379.0, "avg_tokens": 287811.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7361477572559367 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 35.0, "avg_tokens": 29818.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5428571428571428 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 44.0, "avg_tokens": 34697.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7727272727272727 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 24564.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7575757575757576 }, { "model": "gemini-2.5-flash", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 65.0, "avg_tokens": 65880.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6461538461538462 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 25.0, "avg_tokens": 28221.0, "avg_cost_usd": 0.0, "repetition_rate": 0.76 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 40587.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 17446.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 16.0, "avg_tokens": 19131.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6875 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 39776.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 79.0, "avg_tokens": 87262.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8227848101265823 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 31518.0, "avg_cost_usd": 0.0, "repetition_rate": 0.84375 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 46.0, "avg_tokens": 74457.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6739130434782609 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 31349.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6774193548387096 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 109.0, "avg_tokens": 88542.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7981651376146789 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 40.0, "avg_tokens": 39691.0, "avg_cost_usd": 0.0, "repetition_rate": 0.875 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 39541.0, "avg_cost_usd": 0.0, "repetition_rate": 0.4838709677419355 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 251.0, "avg_tokens": 232379.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8406374501992032 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 117.0, "avg_tokens": 100114.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8205128205128205 }, { "model": "gemini-2.5-flash", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 49.0, "avg_tokens": 60306.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7551020408163265 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 17320.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8064516129032258 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 27360.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7428571428571429 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 16.0, "avg_tokens": 9941.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 25116.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 100.0, "avg_tokens": 64273.0, "avg_cost_usd": 0.0, "repetition_rate": 0.67 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 79.0, "avg_tokens": 51318.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7088607594936709 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 41.0, "avg_tokens": 22327.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6829268292682927 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 71.0, "avg_tokens": 60558.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7464788732394366 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 19109.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6060606060606061 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 111.0, "avg_tokens": 66226.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7657657657657657 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 209.0, "avg_tokens": 113182.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7272727272727273 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 31.0, "avg_tokens": 19681.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5161290322580645 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 67.0, "avg_tokens": 39407.0, "avg_cost_usd": 0.0, "repetition_rate": 0.835820895522388 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 24.0, "avg_tokens": 12724.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7916666666666666 }, { "model": "gpt-5.4", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 77.0, "avg_tokens": 56495.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6623376623376623 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 29.0, "avg_tokens": 21057.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8275862068965517 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 32651.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6764705882352942 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15183.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 24393.0, "avg_cost_usd": 0.0, "repetition_rate": 0.72 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 41.0, "avg_tokens": 33740.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6341463414634146 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 28769.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 127.0, "avg_tokens": 87120.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7322834645669292 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 87.0, "avg_tokens": 89823.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7241379310344828 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 22.0, "avg_tokens": 16872.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6818181818181818 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 108.0, "avg_tokens": 81499.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7962962962962963 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 98.0, "avg_tokens": 69530.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7346938775510204 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 31.0, "avg_tokens": 24997.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6774193548387096 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 23163.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8064516129032258 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 58.0, "avg_tokens": 39914.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8103448275862069 }, { "model": "gpt-5.4", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 62.0, "avg_tokens": 55050.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7903225806451613 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 28.0, "avg_tokens": 20768.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8214285714285714 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 33011.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7352941176470589 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15412.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7894736842105263 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 16.0, "avg_tokens": 15075.0, "avg_cost_usd": 0.0, "repetition_rate": 0.625 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 25898.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5483870967741935 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 155.0, "avg_tokens": 127491.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7870967741935484 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 57.0, "avg_tokens": 39047.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7368421052631579 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 4.0, "avg_tokens": 3182.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 25190.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 110.0, "avg_tokens": 84746.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8090909090909091 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 138.0, "avg_tokens": 100165.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6594202898550725 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 41.0, "avg_tokens": 33864.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5853658536585366 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 72.0, "avg_tokens": 55521.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8055555555555556 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 45.0, "avg_tokens": 31834.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "gpt-5.4", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 54.0, "avg_tokens": 48431.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7592592592592593 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 27.0, "avg_tokens": 34853.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8148148148148148 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 23.0, "avg_tokens": 36416.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6521739130434783 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 21861.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 36930.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8387096774193549 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 33.0, "avg_tokens": 40666.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5757575757575758 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 31893.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 35366.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7352941176470589 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 63.0, "avg_tokens": 115474.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6984126984126984 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 40699.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7142857142857143 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 104.0, "avg_tokens": 101897.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 60.0, "avg_tokens": 68160.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8333333333333334 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 50.0, "avg_tokens": 72432.0, "avg_cost_usd": 0.0, "repetition_rate": 0.42 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 87.0, "avg_tokens": 96433.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8505747126436781 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 25846.0, "avg_cost_usd": 0.0, "repetition_rate": 0.72 }, { "model": "gpt-5.4", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 76.0, "avg_tokens": 107937.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7894736842105263 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 25.0, "avg_tokens": 14141.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 19303.0, "avg_cost_usd": 0.0, "repetition_rate": 0.64 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 11779.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7894736842105263 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 25379.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8064516129032258 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 127.0, "avg_tokens": 82685.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7244094488188977 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 82.0, "avg_tokens": 51907.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8170731707317073 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 54.0, "avg_tokens": 28606.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7037037037037037 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 84.0, "avg_tokens": 72836.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 19.0, "avg_tokens": 11158.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5789473684210527 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 107.0, "avg_tokens": 64444.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7289719626168224 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 48.0, "avg_tokens": 26213.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8125 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 31.0, "avg_tokens": 19393.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6451612903225806 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 292.0, "avg_tokens": 177581.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8356164383561644 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 18260.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7428571428571429 }, { "model": "gpt-5.4-mini", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 111.0, "avg_tokens": 82754.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6306306306306306 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 25.0, "avg_tokens": 17740.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 23037.0, "avg_cost_usd": 0.0, "repetition_rate": 0.72 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 20.0, "avg_tokens": 15825.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 30378.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8064516129032258 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 25918.0, "avg_cost_usd": 0.0, "repetition_rate": 0.65625 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 13.0, "avg_tokens": 9970.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6923076923076923 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 20572.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 83.0, "avg_tokens": 84279.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6746987951807228 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 23.0, "avg_tokens": 17128.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6086956521739131 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 118.0, "avg_tokens": 88997.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7627118644067796 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 35.0, "avg_tokens": 24532.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8571428571428571 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 29.0, "avg_tokens": 22880.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6206896551724138 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 94.0, "avg_tokens": 71334.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8297872340425532 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 38.0, "avg_tokens": 25443.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7631578947368421 }, { "model": "gpt-5.4-mini", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 50.0, "avg_tokens": 44165.0, "avg_cost_usd": 0.0, "repetition_rate": 0.68 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 23.0, "avg_tokens": 16745.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8260869565217391 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 22.0, "avg_tokens": 20602.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6818181818181818 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 15128.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7894736842105263 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 26477.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8148148148148148 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 44.0, "avg_tokens": 36071.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6136363636363636 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 147.0, "avg_tokens": 121288.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7619047619047619 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 66.0, "avg_tokens": 44750.0, "avg_cost_usd": 0.0, "repetition_rate": 0.696969696969697 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 87.0, "avg_tokens": 90225.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7126436781609196 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 27120.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7222222222222222 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 107.0, "avg_tokens": 82050.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7757009345794392 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 64.0, "avg_tokens": 46106.0, "avg_cost_usd": 0.0, "repetition_rate": 0.828125 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 37.0, "avg_tokens": 29740.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7027027027027027 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 209.0, "avg_tokens": 160565.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8373205741626795 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 95.0, "avg_tokens": 65421.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4-mini", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 58.0, "avg_tokens": 51711.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7758620689655172 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 35001.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7741935483870968 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 21.0, "avg_tokens": 32329.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7142857142857143 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 20.0, "avg_tokens": 21231.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 30225.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 34972.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6129032258064516 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 109.0, "avg_tokens": 124654.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7706422018348624 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 49.0, "avg_tokens": 44448.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7755102040816326 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 4.0, "avg_tokens": 6100.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 21.0, "avg_tokens": 22967.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7619047619047619 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 100.0, "avg_tokens": 88747.0, "avg_cost_usd": 0.0, "repetition_rate": 0.77 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 65.0, "avg_tokens": 68112.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6923076923076923 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 37450.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6774193548387096 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 145.0, "avg_tokens": 143000.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7931034482758621 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 46.0, "avg_tokens": 40738.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7391304347826086 }, { "model": "gpt-5.4-mini", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 34.0, "avg_tokens": 43632.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6470588235294118 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 25.0, "avg_tokens": 14306.0, "avg_cost_usd": 0.0, "repetition_rate": 0.76 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 27095.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6176470588235294 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Boat", "runs": 1, "success_rate": 0.0, "avg_steps": 11.0, "avg_tokens": 8013.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8181818181818182 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 25501.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7741935483870968 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 32.0, "avg_tokens": 21957.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 41.0, "avg_tokens": 26893.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7073170731707317 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 41.0, "avg_tokens": 19137.0, "avg_cost_usd": 0.0, "repetition_rate": 0.9024390243902439 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 4.0, "avg_tokens": 2529.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 20.0, "avg_tokens": 12002.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 109.0, "avg_tokens": 65841.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8073394495412844 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 73.0, "avg_tokens": 41214.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7397260273972602 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Pizza_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 30.0, "avg_tokens": 19278.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5666666666666667 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 600.0, "avg_tokens": 378530.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8616666666666667 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 27.0, "avg_tokens": 14676.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7777777777777778 }, { "model": "qwen-2.5-72b-instruct", "mode": "stub", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 78.0, "avg_tokens": 62043.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7307692307692307 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 29.0, "avg_tokens": 20861.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7931034482758621 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 26.0, "avg_tokens": 24353.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6538461538461539 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Boat", "runs": 1, "success_rate": 0.0, "avg_steps": 16.0, "avg_tokens": 13514.0, "avg_cost_usd": 0.0, "repetition_rate": 0.75 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 30.0, "avg_tokens": 28426.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7333333333333333 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 75.0, "avg_tokens": 62328.0, "avg_cost_usd": 0.0, "repetition_rate": 0.68 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 43.0, "avg_tokens": 34105.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7906976744186046 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 56.0, "avg_tokens": 34879.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8214285714285714 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 50.0, "avg_tokens": 49706.0, "avg_cost_usd": 0.0, "repetition_rate": 0.78 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 24.0, "avg_tokens": 17636.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 98.0, "avg_tokens": 75704.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7448979591836735 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 56.0, "avg_tokens": 38725.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8392857142857143 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 51.0, "avg_tokens": 39835.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6078431372549019 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 71.0, "avg_tokens": 53559.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8169014084507042 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 22710.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7352941176470589 }, { "model": "qwen-2.5-72b-instruct", "mode": "reasoning", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 28267.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5483870967741935 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 28.0, "avg_tokens": 20179.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8214285714285714 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 26.0, "avg_tokens": 24777.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6153846153846154 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 16176.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8421052631578947 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 29752.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7419354838709677 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 48.0, "avg_tokens": 40633.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7083333333333334 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 29758.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 47.0, "avg_tokens": 31889.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7659574468085106 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 55.0, "avg_tokens": 55291.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7272727272727273 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 21.0, "avg_tokens": 15862.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 97.0, "avg_tokens": 75025.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7835051546391752 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 42.0, "avg_tokens": 29129.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8571428571428571 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 28260.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 414.0, "avg_tokens": 324471.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8502415458937198 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 79.0, "avg_tokens": 53412.0, "avg_cost_usd": 0.0, "repetition_rate": 0.810126582278481 }, { "model": "qwen-2.5-72b-instruct", "mode": "light_hints", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 36.0, "avg_tokens": 33238.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6111111111111112 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Badday_eng", "runs": 1, "success_rate": 1.0, "avg_steps": 25.0, "avg_tokens": 27164.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Banket_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 22.0, "avg_tokens": 32696.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6818181818181818 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Boat", "runs": 1, "success_rate": 1.0, "avg_steps": 19.0, "avg_tokens": 20485.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7894736842105263 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Codebox_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 25.0, "avg_tokens": 25217.0, "avg_cost_usd": 0.0, "repetition_rate": 0.68 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Depth_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 37.0, "avg_tokens": 41676.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7297297297297297 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Driver_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 15.0, "avg_tokens": 17002.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6666666666666666 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Edelweiss_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 31.0, "avg_tokens": 26003.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7741935483870968 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Election_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 42.0, "avg_tokens": 65542.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7142857142857143 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Foncers_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 23.0, "avg_tokens": 23006.0, "avg_cost_usd": 0.0, "repetition_rate": 0.6521739130434783 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Leonardo_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 104.0, "avg_tokens": 82293.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7884615384615384 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Ministry_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 159.0, "avg_tokens": 155859.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8238993710691824 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Pizza_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 18.0, "avg_tokens": 20229.0, "avg_cost_usd": 0.0, "repetition_rate": 0.5 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Prison_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 80.0, "avg_tokens": 71809.0, "avg_cost_usd": 0.0, "repetition_rate": 0.775 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Robots_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 93.0, "avg_tokens": 78455.0, "avg_cost_usd": 0.0, "repetition_rate": 0.8064516129032258 }, { "model": "qwen-2.5-72b-instruct", "mode": "planner", "quest": "Ski_eng", "runs": 1, "success_rate": 0.0, "avg_steps": 34.0, "avg_tokens": 41557.0, "avg_cost_usd": 0.0, "repetition_rate": 0.7058823529411765 } ] }