Tool Use on TAU-2 & BFCL-V4 Multi-turn
52Average ScoreQwen3-235B-A22B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-235B-A22B-InstructReasoning Method=non-thinking, using tools2026.04 | 52 | |
| AgenticQwen-30B-A3BReasoning Method=non-thinking, using tools2026.04 | 50.2 | |
| AgenticQwen-8BReasoning Method=non-thinking, using tools2026.04 | 47.4 | |
| Qwen3-30B-A3B-InstructReasoning Method=non-thinking, using tools2026.04 | 36.2 | |
| Qwen3-32BReasoning Method=non-thinking, using tools2026.04 | 36 | |
| Qwen3-8BReasoning Method=non-thinking, using tools2026.04 | 23.8 |