Workflow Planning on WorfBench
80.3F1 ChainMagicAgent-32B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MagicAgent-32BModel Category=MagicAgent Series2026.02 | 80.3 | 69.7 | |
| MagicAgent-30B-A3BModel Category=MagicAgent Series2026.02 | 79.6 | 69.9 | |
| GLM-4.7Model Category=Ultra-Scale2026.02 | 67.3 | 49.8 | |
| Kimi-K2-InstructModel Category=Ultra-Scale2026.02 | 66.9 | 49.2 | |
| Qwen3-32B-nothinkModel Category=Large-Scale2026.02 | 65.8 | 49.2 | |
| DeepSeek-V3.1-nothinkModel Category=Ultra-Scale2026.02 | 65.6 | 47.1 | |
| Qwen3-MAXModel Category=Ultra-Scale2026.02 | 65.4 | 47.6 | |
| GLM-4.7-FlashModel Category=Large-Scale2026.02 | 64.5 | 47.4 | |
| Qwen3-235B-A22B-InstructModel Category=Ultra-Scale2026.02 | 63.2 | 44.7 | |
| Qwen3-30B-A3B-InstructModel Category=Large-Scale2026.02 | 62.4 | 44.4 | |
| Llama3.3-70B-InstructModel Category=Large-Scale2026.02 | 62.3 | 43.8 | |
| ERNIE-4.5-21B-A3B-PTModel Category=Large-Scale2026.02 | 61.2 | 41.1 | |
| GPT-5.2Model Category=Ultra-Scale2026.02 | 60.1 | 39.1 | |
| Olmo-3.1-32B-InstructModel Category=Large-Scale2026.02 | 33.2 | 22.7 |