List your company

Robustness of Tool-use on RoTBench

78.76TSGPT 4o
38.158448.699259.2469.7808Aug 12, 2025

Evaluation results

MethodLinks
GPT 4oVersion=4o2025.0878.7649.4331.52
Qwen3-8B Non-Reasoning FTRL-Reinforce++Family=Qwen3-8B, Version=Non-Reasoning, Method=FTRL-Reinforce++2025.0878.142.5725.9
Qwen3-14B Non-Reasoning FTRL-Reinforce++Family=Qwen3-14B, Version=Non-Reasoning, Method=FTRL-Reinforce++2025.0877.8142.5725.24
Qwen3-8B Non-Reasoning FTRL-GRPOFamily=Qwen3-8B, Version=Non-Reasoning, Method=FTRL-GRPO2025.0877.6244.6727.05
Qwen3-14B Non-ReasoningFamily=Qwen3-14B, Version=Non-Reasoning2025.0875.936.3820.67
Qwen3-8B Non-ReasoningFamily=Qwen3-8B, Version=Non-Reasoning2025.0875.5236.2922.19
Qwen2.5-32B InstructFamily=Qwen2.5-32B, Version=Instruct2025.0875.4336.8620
Qwen3-14B Non-Reasoning FTRL-GRPOFamily=Qwen3-14B, Version=Non-Reasoning, Method=FTRL-GRPO2025.0875.3340.9522.48
Qwen2.5-7B FTRL-GRPOFamily=Qwen2.5-7B, Method=FTRL-GRPO2025.087430.8618.95
Qwen3-32B Non-ReasoningFamily=Qwen3-32B, Version=Non-Reasoning2025.0873.2441.7124.86
Qwen2.5-14B FTRL-Reinforce++Family=Qwen2.5-14B, Method=FTRL-Reinforce++2025.0873.0545.2428.19
Qwen2.5-72B InstructFamily=Qwen2.5-72B, Version=Instruct2025.0872.1926.2917.14
Qwen2.5-14B InstructFamily=Qwen2.5-14B, Version=Instruct2025.0871.8138.2921.33
Qwen2.5-14B FTRL-GRPOFamily=Qwen2.5-14B, Method=FTRL-GRPO2025.0871.5236.1921.62
Qwen2.5-7B FTRL-Reinforce++Family=Qwen2.5-7B, Method=FTRL-Reinforce++2025.0870.9540.9526.1
Qwen2.5-7B InstructFamily=Qwen2.5-7B, Version=Instruct2025.0870.3827.3315.43
GPT 3.5-TurboVersion=3.5-Turbo2025.0865.7129.8117.33
Qwen3-14B Reasoning FTRL-GRPOFamily=Qwen3-14B, Version=Reasoning, Method=FTRL-GRPO2025.0860.5738.121.43
Qwen3-14B Reasoning FTRL-Reinforce++Family=Qwen3-14B, Version=Reasoning, Method=FTRL-Reinforce++2025.0858.9537.2421.62
Qwen3-14B ReasoningFamily=Qwen3-14B, Version=Reasoning2025.0857.3336.1920.29
Qwen3-8B Reasoning FTRL-GRPOFamily=Qwen3-8B, Version=Reasoning, Method=FTRL-GRPO2025.0854.5739.2422.95
Qwen3-8B ReasoningFamily=Qwen3-8B, Version=Reasoning2025.085434.2920.38
Qwen3-32B ReasoningFamily=Qwen3-32B, Version=Reasoning2025.0853.933.8120.19
Gemini 2.5-FlashVersion=2.5-Flash2025.0853.6234.9522.76
Qwen3-8B Reasoning FTRL-Reinforce++Family=Qwen3-8B, Version=Reasoning, Method=FTRL-Reinforce++2025.0853.5237.5222.29
Gemini 2.5-ProVersion=2.5-Pro2025.0849.0542.3827.52
Claude 4.0-SonnetVersion=4.0-Sonnet2025.0839.7234.9521.81