General Knowledge on MMLU-Pro (EM)
84MMLU-Pro General Knowledge EMDeepSeek-R1
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DeepSeek-R1Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 84 | — | |
| K-EXAONE-236B-A23BReasoning=On2026.03 | 83.4 | — | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=On2026.03 | 81.8 | — | |
| K-EXAONE-236B-A23BReasoning=Off2026.03 | 80.96 | — | |
| OpenAI-o1-mini2025.01 | 80.3 | — | |
| OpenAI o1-miniModel Backbone=o1-mini2026.03 | 80.3 | — | |
| Qwen-3-30B-A3BReasoning=On2026.03 | 80.1 | — | |
| Solar-Open-100BReasoning=On2026.03 | 79.77 | — | |
| Nemotron-3-Ultra 550B-A55B-Baseshots=5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 79.07 | — | |
| Qwen-3-30B-A3BReasoning=Off2026.03 | 78.67 | — | |
| HyperCLOVAX-SEED-Think-32BReasoning=On2026.03 | 78.5 | — | |
| Claude-3.5-Sonnet-10222025.01 | 78 | — | |
| Claude 3.5 Sonnet-1022Model Backbone=Claude 3.5 Sonnet2026.03 | 78 | — | |
| DeepSeek-V3Architecture=MoE, Activated Params=37B, Total Params=671B2025.01 | 75.9 | — | |
| Mi:dm K 2.5 Pro (March ‘26)Reasoning=Off2026.03 | 73.98 | — | |
| GPT-4o-05132025.01 | 72.6 | — | |
| GPT-4o 0513Model Backbone=GPT-4o2026.03 | 72.6 | — | |
| Kimi-K2 Baseshots=5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 69.15 | — | |
| R1-Distill-Qwen-14BModel Backbone=Qwen-14B2026.03 | 68.8 | — | |
| Mistral-Large-3 675B-Base-2512shots=5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 67.42 | — | |
| HyperCLOVAX-SEED-Think-32BReasoning=Off2026.03 | 67.31 | — | |
| MiMo-RL 7B-R-TAPModel Backbone=7B2026.03 | 65.9 | — | |
| GLM-4.5 Baseshots=5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 65.78 | — | |
| DeepSeek-V3.2 Exp-Baseshots=5-shot, reasoning=Chain-of-thought (CoT)2026.06 | 63.26 | — | |
| MiMo 7B-RLModel Backbone=7B2026.03 | 58.6 | — | |
| R1-Distill-Qwen-7BModel Backbone=Qwen-7B2026.03 | 53.5 | — | |
| QwQ-32B PreviewModel Backbone=QwQ-32B2026.03 | 52 | — | |
| GLM-4.5 Air-BaseShots=5, Chain-of-Thought (CoT)=true2026.04 | — | 58.2 | |
| Ling-flash base-2.0Shots=5, Chain-of-Thought (CoT)=true2026.04 | — | 62.1 | |
| N-3-Super 120B-A12B-BaseShots=5, Chain-of-Thought (CoT)=true2026.04 | — | 75.65 |