[{"rank":1,"filename":".eval_results/evasionbench.yaml","value":82.91,"verified":false,"source":{"url":"https://arxiv.org/abs/2601.09142","name":"EvasionBench Paper","isExternal":true},"pullRequest":43,"modelId":"zai-org/GLM-4.7","author":{"_id":"62ad27f19096e7f9ecb1853a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png","fullname":"Z.ai","name":"zai-org","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"plan":"team","followerCount":22137,"isUserFollowing":false},"lower_is_better":false,"num_parameters":358337791296},{"rank":2,"filename":".eval_results/evasionbench.yaml","value":78.16,"verified":false,"source":{"url":"https://arxiv.org/abs/2601.09142","name":"EvasionBench Paper","isExternal":true},"pullRequest":31,"modelId":"Qwen/Qwen3-Coder-480B-A35B-Instruct","author":{"_id":"64c8b5837fe12ecd0a7e92eb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg","fullname":"Qwen","name":"Qwen","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"plan":"team","followerCount":109755,"isUserFollowing":false},"lower_is_better":false,"num_parameters":480154875392},{"rank":3,"filename":".eval_results/evasionbench.yaml","value":77.83,"verified":false,"source":{"url":"https://huggingface.co/datasets/FutureMa/EvasionBench","name":"EvasionBench","isExternal":true,"author":{"_id":"6905bc786cb49b1f11d32728","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/504I_H8J9NkiytiHvbx-h.jpeg","fullname":"VIDRAFT_LAB","name":"SeaWolf-AI","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":376,"isUserFollowing":false}},"modelId":"FINAL-Bench/Darwin-180B-RSI-R3","author":{"_id":"699976ab4a856643b7429675","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6905bc786cb49b1f11d32728/VZmuKH-liifeL2GCXlwka.jpeg","fullname":"FINAL_Bench","name":"FINAL-Bench","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"plan":"team","followerCount":375,"isUserFollowing":false},"notes":"Own evaluation with inspect-ai, task as defined in the dataset eval.yaml (split train, 16,726 samples, shuffle_choices, multiple_choice template, choice scorer, accuracy). Served checkpoint: FINAL-Bench/Darwin-180B-RSI-R3 (BF16) on vLLM; temperature 1.0, top_p 0.95, max_tokens 8192, default chat template; 13,018 of 16,726 correct, single run.","lower_is_better":false,"num_parameters":179999981459},{"rank":4,"filename":".eval_results/evasionbench.yaml","value":71.31,"verified":false,"source":{"url":"https://arxiv.org/abs/2601.09142","name":"EvasionBench Paper","isExternal":true},"pullRequest":27,"modelId":"MiniMaxAI/MiniMax-M2.1","author":{"_id":"6778fc29920093dbc0c24917","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg","fullname":"MiniMax","name":"MiniMaxAI","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"plan":"team","followerCount":11151,"isUserFollowing":false},"lower_is_better":false,"num_parameters":228689764864},{"rank":5,"filename":".eval_results/evasionbench.yaml","value":66.68,"verified":false,"source":{"url":"https://arxiv.org/abs/2601.09142","name":"EvasionBench Paper","isExternal":true},"pullRequest":23,"modelId":"moonshotai/Kimi-K2-Instruct-0905","author":{"_id":"6425a114812813f8f4a9b02c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg","fullname":"Moonshot AI","name":"moonshotai","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"plan":"team","followerCount":19461,"isUserFollowing":false},"lower_is_better":false,"num_parameters":1026470735448}]