Claw-Eval Leaderboard

Benchmark Model Rank Results
agents-on-claw-eval-general-pass-3MiMo-V2.5-Pro (General)#1Pass^3: 64.0
agents-on-claw-eval-general-pass-3GLM-5.1 (General)#2Pass^3: 62.7
agents-on-claw-eval-general-pass-3Kimi-K2.6 (General)#3Pass^3: 61.5
agents-on-claw-eval-general-pass-3DeepSeek-V4-Pro (General)#4Pass^3: 58.4
agents-on-claw-eval-general-pass-3DeepSeek-V4-Flash (General)#6Pass^3: 57.8
agents-on-claw-eval-general-pass-3Kimi-K2.5 (General)#7Pass^3: 52.8
agents-on-claw-eval-multi-turn-pass-3Kimi-K2.6 (Multi Turn)#1Pass^3: 65.8
agents-on-claw-eval-multi-turn-pass-3DeepSeek-V4-Pro (Multi Turn)#2Pass^3: 65.8
agents-on-claw-eval-multi-turn-pass-3MiMo-V2.5-Pro (Multi Turn)#3Pass^3: 63.2
agents-on-claw-eval-multi-turn-pass-3GLM-5.1 (Multi Turn)#4Pass^3: 60.5
agents-on-claw-eval-multi-turn-pass-3DeepSeek-V4-Flash (Multi Turn)#6Pass^3: 57.9
agents-on-claw-eval-multi-turn-pass-3Kimi-K2.5 (Multi Turn)#8Pass^3: 50.0