Cross-Lingual Planning on ACEBench
78.3Score (En)MagicAgent-32B
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MagicAgent-32BModel Category=MagicAgent Series2026.02 | 78.3 | 84.1 | |
| GLM-4.7Model Category=Ultra-Scale2026.02 | 78.2 | 87 | |
| Qwen3-MAXModel Category=Ultra-Scale2026.02 | 77.6 | 86.6 | |
| Kimi-K2-InstructModel Category=Ultra-Scale2026.02 | 77.4 | 83.3 | |
| MagicAgent-30B-A3BModel Category=MagicAgent Series2026.02 | 74.9 | 83.5 | |
| GPT-5.2Model Category=Ultra-Scale2026.02 | 70.7 | 80.1 | |
| Qwen3-235B-A22B-InstructModel Category=Ultra-Scale2026.02 | 70.1 | 77.1 | |
| DeepSeek-V3.1-nothinkModel Category=Ultra-Scale2026.02 | 67.8 | 73.2 | |
| Qwen3-30B-A3B-InstructModel Category=Large-Scale2026.02 | 61.3 | 71.1 | |
| Qwen3-32B-nothinkModel Category=Large-Scale2026.02 | 57.2 | 70.1 | |
| Llama3.3-70B-InstructModel Category=Large-Scale2026.02 | 56.7 | 61.7 | |
| GLM-4.7-FlashModel Category=Large-Scale2026.02 | 53.5 | 62 | |
| ERNIE-4.5-21B-A3B-PTModel Category=Large-Scale2026.02 | 46.9 | 51.1 | |
| Olmo-3.1-32B-InstructModel Category=Large-Scale2026.02 | 25.1 | 18.4 |