List your company

Tool Use on TAU-2 & BFCL-V4 Multi-turn

52Average ScoreQwen3-235B-A22B-Instruct
22.67230.28637.945.514Apr 23, 2026

Evaluation results

MethodLinks
Qwen3-235B-A22B-InstructReasoning Method=non-thinking, using tools2026.0452
AgenticQwen-30B-A3BReasoning Method=non-thinking, using tools2026.0450.2
AgenticQwen-8BReasoning Method=non-thinking, using tools2026.0447.4
Qwen3-30B-A3B-InstructReasoning Method=non-thinking, using tools2026.0436.2
Qwen3-32BReasoning Method=non-thinking, using tools2026.0436
Qwen3-8BReasoning Method=non-thinking, using tools2026.0423.8