Tool Selection on Chess Skill: beginner, intermediate, advanced
100AccuracyGold (Ground Truth Documentation)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gold (Ground Truth Documentation)Model=GPT-5, Framework=ReAct2026.02 | 100 | 2,341 | |
| Gold (Ground Truth Documentation)Model=GPT-5-mini, Framework=ReAct2026.02 | 100 | 2,346 | |
| TOOLOBSERVERModel=GPT-5, Framework=ReAct2026.02 | 29.1 | 1,756 | |
| TOOLOBSERVERModel=GPT-5-mini, Framework=ReAct2026.02 | 28.4 | 1,778 | |
| Base (Opacified set)Model=GPT-5-mini, Framework=ReAct2026.02 | 25.7 | 1,674 | |
| EasyToolModel=GPT-5-mini, Framework=ReAct2026.02 | 25.5 | 1,645 | |
| Base (Opacified set)Model=GPT-5, Framework=ReAct2026.02 | 24.9 | 1,572 | |
| EasyToolModel=GPT-5, Framework=ReAct2026.02 | 24.9 | 1,584 | |
| Play2PromptModel=GPT-5-mini, Framework=ReAct2026.02 | 22.7 | 1,481 | |
| Play2PromptModel=GPT-5, Framework=ReAct2026.02 | 0.25 | 1,622 |