STEM Knowledge on MMLU-Pro
84.3AccuracyDeepSeek V3.2
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek V3.2Evaluation Mode=Chat2025.12 | 84.3 | |
| LongCat-Flash Exp-ChatEvaluation Mode=Chat2025.12 | 84 | |
| LongCat-Flash ChatEvaluation Mode=Chat2025.12 | 82.7 | |
| GLM 4.6Evaluation Mode=Chat2025.12 | 81.5 |