Function Calling on ACEBench Special
87.6Overall ScoreGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4osetting=Zero-shot2026.04 | 87.6 | |
| GENESISFUNC-8Bsetting=Zero-shot2026.04 | 83.67 | |
| GPT-4o-minisetting=Zero-shot2026.04 | 79.9 | |
| Gemini-1.5-Prosetting=Zero-shot2026.04 | 79 | |
| Qwen-ToolRL-8Bsetting=Zero-shot2026.04 | 78.67 | |
| Qwen3-8Bsetting=Zero-shot2026.04 | 76.67 | |
| LLaMA-3.1-8B-Instructsetting=Zero-shot2026.04 | 46.6 | |
| ToolACE-8Bsetting=Zero-shot2026.04 | 1 |