List your company

Tool Selection on Chess Skill: beginner, intermediate, advanced

100AccuracyGold (Ground Truth Documentation)
-3.7423.192550.12577.0575Feb 16, 2026

Evaluation results

MethodLinks
Gold (Ground Truth Documentation)Model=GPT-5, Framework=ReAct2026.021002,341
Gold (Ground Truth Documentation)Model=GPT-5-mini, Framework=ReAct2026.021002,346
TOOLOBSERVERModel=GPT-5, Framework=ReAct2026.0229.11,756
TOOLOBSERVERModel=GPT-5-mini, Framework=ReAct2026.0228.41,778
Base (Opacified set)Model=GPT-5-mini, Framework=ReAct2026.0225.71,674
EasyToolModel=GPT-5-mini, Framework=ReAct2026.0225.51,645
Base (Opacified set)Model=GPT-5, Framework=ReAct2026.0224.91,572
EasyToolModel=GPT-5, Framework=ReAct2026.0224.91,584
Play2PromptModel=GPT-5-mini, Framework=ReAct2026.0222.71,481
Play2PromptModel=GPT-5, Framework=ReAct2026.020.251,622