Agentic Tool Calling on Tau (Domain Scores)
56Airline ScoreMAVEN
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MAVENBase Model=GPT-OSS-120b2026.05 | 56 | 75.65 | |
| o3Model Identifier=o3-2025-04-162026.05 | 52 | 70.4 | |
| Kimi-K2Model Identifier=Kimi-K22026.05 | 51.2 | 73.9 | |
| o4-miniModel Identifier=o4-mini-2025-04-162026.05 | 46 | 70.4 | |
| Qwen3-Th-235BModel Identifier=Qwen3-235B2026.05 | 46 | 67.8 | |
| GPT-5Model Identifier=gpt-5-2025-08-072026.05 | 44 | 78.3 | |
| Gemini-2.5Model Identifier=gemini-2.5-pro-preview-05-062026.05 | 44 | 68.7 | |
| DeepSeek-V3.1Model Identifier=DeepSeek-V3.12026.05 | 40 | 66.1 |