Agentic Tool Use on τ²-Bench Airline
67.5AccuracyQwen3.5-27B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3.5-27BArchitecture=Dense, # Total Params=27B, # Activated Params=27B, Reasoning Mode=REASONING2026.04 | 67.5 | |
| Qwen3-VL-235B-A22BArchitecture=MoE, # Total Params=236B, # Activated Params=22B, Reasoning Mode=Thinking2026.04 | 62 | |
| K-EXAONE-236B-A23BArchitecture=MoE, # Total Params=236B, # Activated Params=23B, Reasoning Mode=REASONING2026.04 | 60.4 | |
| GPT-5 miniReasoning Mode=REASONING: HIGH2026.04 | 60 | |
| EXAONE 4.5 33BArchitecture=Dense, # Total Params=33B, # Activated Params=32B, Reasoning Mode=REASONING2026.04 | 56.5 |