Multilingual Knowledge on MMLU ProX
86.4AccuracyQwen-3.5
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen-3.5Parameter Count=397B-17B2026.06 | 86.4 | |
| GLM-5.1Parameter Count=744B-A40B2026.06 | 85.8 | |
| DS-v4-ProParameter Count=1.6T-A49B2026.06 | 85.6 | |
| Qwen3.5-122B-A10B2026.04 | 85.06 | |
| Kimi-K2.6Parameter Count=1T-A32B2026.06 | 85 | |
| DS-v4-FlashParameter Count=284B-A13B2026.06 | 84.3 | |
| Nemotron 3 UltraParameter Count=550B-A55B2026.06 | 83 | |
| Nemotron 3 Super2026.04 | 79.36 | |
| MiniMax-2.7Parameter Count=230B-A10B2026.06 | 78.4 | |
| GPT-OSS-120B2026.04 | 76.59 |