Agentic Tool Calling on Mixed Overall Summary
67.28Overall Success RateMAVEN
Evaluation Results
| Method | Links | |
|---|---|---|
| MAVENBase Model=GPT-OSS-120b2026.05 | 67.28 | |
| Kimi-K2Model Identifier=Kimi-K22026.05 | 63.07 | |
| GPT-5Model Identifier=gpt-5-2025-08-072026.05 | 61.15 | |
| o3Model Identifier=o3-2025-04-162026.05 | 58.61 | |
| o4-miniModel Identifier=o4-mini-2025-04-162026.05 | 56.04 | |
| Qwen3-Th-235BModel Identifier=Qwen3-235B2026.05 | 52.26 | |
| Gemini-2.5Model Identifier=gemini-2.5-pro-preview-05-062026.05 | 50.14 | |
| DeepSeek-V3.1Model Identifier=DeepSeek-V3.12026.05 | 47.93 |