A multiple-choice benchmark spanning 57 subjects that evaluates the knowledge and reasoning capabilities of large language models.
Browse the latest scores, model modes, release dates, and parameter sizes for MMLU.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 DeepSeek-V3.1 Thinking Enabled | 93.40 | 2025-08-20 | 671B | Free Commercial | |
 OpenAI o4 - mini Thinking Enabled | 93.00 | 2025-04-16 | Unknown | Closed | |
 Gemini 3.1 Pro Preview Thinking Level · High | 92.60 | 2026-02-20 | Unknown | Closed | |
4 | OpenAI o1 Standard Mode | 91.80 | 2024-12-05 | Unknown | Closed |
5 | DeepSeek-V3.1 Standard Mode | 91.80 | 2025-08-20 | 671B | Free Commercial |
6 |  Opus 4.7 Standard Mode | 91.50 | 2026-04-16 | Unknown | Closed |
7 | Claude Opus 4.6 Extended Thinking | 91.05 | 2026-02-05 | Unknown | Closed |
8 | DeepSeek-R1 Standard Mode | 90.80 | 2025-01-20 | 671B | Free Commercial |
9 | GPT-4.1 Standard Mode | 90.20 | 2025-04-14 | Unknown | Closed |
10 | GPT OSS 120B Thinking Enabled | 90.00 | 2025-08-06 | 11.7B | Free Commercial |
11 | GPT-5.2 Thinking Level · Extra High | 89.60 | 2025-12-11 | Unknown | Closed |
12 |  Hunyuan-TurboS Standard Mode | 89.50 | 2025-03-10 | Unknown | Closed |
13 |  Kimi K2 Standard Mode | 89.50 | 2025-07-11 | 1000B | Free Commercial |
14 |  Pangu Pro MoE Standard Mode | 89.30 | 2025-06-30 | 71.9B | Free Commercial |
15 | GPT-4o Standard Mode | 88.70 | 2024-05-13 | Unknown | Closed |
16 |  Llama3.1-405B Instruct Standard Mode | 88.60 | 2024-07-23 | 405B | Free Commercial |
17 | DeepSeek-V3 Standard Mode | 88.50 | 2024-12-26 | 681B | Free Commercial |
18 | Claude 3.5 Sonnet Standard Mode | 88.30 | 2024-06-21 | Unknown | Closed |
19 | Claude 3.5 Sonnet New Standard Mode | 88.30 | 2024-10-22 | Unknown | Closed |
20 | Hunyuan-A13B-Instruct Standard Mode | 88.17 | 2025-06-27 | 80B | Free Commercial |
21 |  Qwen2.5-Max Standard Mode | 87.90 | 2025-01-28 | Unknown | Closed |
22 |  Grok 2 Standard Mode | 87.50 | 2024-08-13 | 269B | Free Commercial |
23 | GPT-4.1 mini Standard Mode | 87.50 | 2025-04-14 | Unknown | Closed |
24 | Kimi k1.5 (Short-CoT) Standard Mode | 87.40 | 2025-01-22 | Unknown | Closed |
25 | Gemini 1.5 Pro Standard Mode | 87.10 | 2024-02-15 | Unknown | Closed |
26 | OpenAI o3-mini (high) Standard Mode | 86.90 | 2025-01-31 | Unknown | Closed |
27 | Claude3-Opus Standard Mode | 86.80 | 2024-03-04 | Unknown | Closed |
28 |  Gemini 2.0 Pro Experimental Standard Mode | 86.50 | 2025-02-05 | Unknown | Closed |
29 | DeepSeek-V3-0324 Standard Mode | 86.50 | 2025-03-24 | 671B | Free Commercial |
30 |  ERNIE-4.5-300B-A47B Standard Mode | 86.50 | 2025-06-30 | 300B | Free Commercial |
