Knowledge benchmark

# MMLU leaderboard

> MMLU results for 81 AI models, led by GPT-4o at 88.1%. What the benchmark measures, who runs it, and a source for every score.
- Canonical page: https://noometry.com/benchmarks/mmlu
- Last updated: 2026-10-10
- Title: MMLU Leaderboard (October 2026): Scores by Model | Noometry

As of October 2026, GPT-4o has the highest published MMLU score on Noometry at 88.1%, out of 81 models with results.

Last verified October 10, 2026

## About MMLU

57-subject multiple-choice exam covering STEM, humanities and professional topics.

- **Category:** [Knowledge](https://noometry.com/best/knowledge)
- **Introduced:** 2020
- **Size:** About 14,000 questions
- **Format:** Multiple choice (4 options)
- **Unit:** Percent (random guessing ≈ 25%)
- **Official site:** [arxiv.org](https://arxiv.org/abs/2009.03300)

## Top 15 models

Top models on MMLU

1.  GPT-4o 88.1%
2.  Claude 3.5 Sonnet 87.3%
3.  DeepSeek-V3 87.2%
4.  Gemini 1.5 Pro (May 2024) 86.9%
5.  GPT-4 86.4%
6.  Llama-3.3-70B-Instruct 86.3%
7.  Qwen2.5 72B Instruct 85.3%
8.  Phi-4 84.8%
9.  Claude 3 Opus 84.6%
10.  Llama 3.1-405B 84.5%
11.  Qwen2-72B 82.4%
12.  Amazon Nova Pro 82%
13.  GPT-4o mini 81.8%
14.  GPT-4 Turbo 81.3%
15.  Llama 3.2 90B 80.3%
16.  78808284868890

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## All results

MMLU results by model
| # | Model | Provider | Score | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | [GPT-4o](https://noometry.com/models/gpt-4o) | [OpenAI](https://noometry.com/providers/openai) | 88.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 2 | [Claude 3.5 Sonnet](https://noometry.com/models/claude-3-5-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 87.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 3 | [DeepSeek-V3](https://noometry.com/models/deepseek-v3) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 87.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 4 | [Gemini 1.5 Pro (May 2024)](https://noometry.com/models/gemini-1-5-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 86.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 5 | [GPT-4](https://noometry.com/models/gpt-4) | [OpenAI](https://noometry.com/providers/openai) | 86.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 6 | [Llama-3.3-70B-Instruct](https://noometry.com/models/llama-3-3-70b-instruct) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 86.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 7 | [Qwen2.5 72B Instruct](https://noometry.com/models/qwen2-5-72b-instruct) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 85.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 8 | [Phi-4](https://noometry.com/models/phi-4) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 84.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 9 | [Claude 3 Opus](https://noometry.com/models/claude-3-opus) | [Anthropic](https://noometry.com/providers/anthropic) | 84.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 10 | [Llama 3.1-405B](https://noometry.com/models/llama-3-1-405b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 84.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 11 | [Qwen2-72B](https://noometry.com/models/qwen2-72b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 82.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 12 | [Amazon Nova Pro](https://noometry.com/models/amazon-nova-pro) | [Amazon](https://noometry.com/providers/amazon) | 82% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 13 | [GPT-4o mini](https://noometry.com/models/gpt-4o-mini) | [OpenAI](https://noometry.com/providers/openai) | 81.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 14 | [GPT-4 Turbo](https://noometry.com/models/gpt-4-turbo) | [OpenAI](https://noometry.com/providers/openai) | 81.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 15 | [Llama 3.2 90B](https://noometry.com/models/llama-3-2-90b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 80.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 16 | [Llama 3.1-70B](https://noometry.com/models/llama-3-1-70b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 80.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 17 | [Mistral Large](https://noometry.com/models/mistral-large) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 80% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 18 | [Qwen2.5 14B Instruct](https://noometry.com/models/qwen2-5-14b-instruct) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 79.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 19 | [Gemini 2.0 Flash (Feb 2025)](https://noometry.com/models/gemini-2-0-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 79.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 20 | [Llama 3-70B](https://noometry.com/models/llama-3-70b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 79.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 21 | [Yi-Large](https://noometry.com/models/yi-large) | [01.AI](https://noometry.com/providers/01-ai) | 79.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 22 | [Qwen2.5-Coder-32B](https://noometry.com/models/qwen2-5-coder-32b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 79.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 23 | [Claude 2](https://noometry.com/models/claude-2) | [Anthropic](https://noometry.com/providers/anthropic) | 78.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 24 | [DeepSeek-V2 (MoE-236B, May 2024)](https://noometry.com/models/deepseek-v2) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 78.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 25 | [phi-3-medium 14B](https://noometry.com/models/phi-3-medium-14b) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 78% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 26 | [Gemini 1.5 Flash (May 2024)](https://noometry.com/models/gemini-1-5-flash) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 77.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 27 | [Mixtral 8x22B](https://noometry.com/models/mixtral-8x22b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 77.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 28 | [Amazon Nova Lite](https://noometry.com/models/amazon-nova-lite) | [Amazon](https://noometry.com/providers/amazon) | 77% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 29 | [Claude 1.3](https://noometry.com/models/claude-1-3) | [Anthropic](https://noometry.com/providers/anthropic) | 77% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 30 | [Yi-34B](https://noometry.com/models/yi-34b) | [01.AI](https://noometry.com/providers/01-ai) | 76.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 31 | [Claude 3 Sonnet](https://noometry.com/models/claude-3-sonnet) | [Anthropic](https://noometry.com/providers/anthropic) | 75.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 32 | [Gemma 2 27B](https://noometry.com/models/gemma-2-27b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 75.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 33 | [Phi 3 Small 8k Instruct](https://noometry.com/models/phi-3-small-8k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 75.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 34 | [Qwen1.5-32B](https://noometry.com/models/qwen1-5-32b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 74.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 35 | [Claude 3.5 Haiku](https://noometry.com/models/claude-3-5-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 74.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 36 | [Claude 3 Haiku](https://noometry.com/models/claude-3-haiku) | [Anthropic](https://noometry.com/providers/anthropic) | 73.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 37 | [Claude 2.1](https://noometry.com/models/claude-2-1) | [Anthropic](https://noometry.com/providers/anthropic) | 73.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 38 | [Claude Instant](https://noometry.com/models/claude-instant) | [Anthropic](https://noometry.com/providers/anthropic) | 73.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 39 | [Qwen2.5 7B Instruct](https://noometry.com/models/qwen2-5-7b-instruct) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 72.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 40 | [Gemma 2 9B](https://noometry.com/models/gemma-2-9b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 72.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 41 | [GPT-3.5-turbo](https://noometry.com/models/gpt-3-5-turbo) | [OpenAI](https://noometry.com/providers/openai) | 71.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 42 | [Amazon Nova Micro](https://noometry.com/models/amazon-nova-micro) | [Amazon](https://noometry.com/providers/amazon) | 70.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 43 | [Falcon-180B](https://noometry.com/models/falcon-180b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 70.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 44 | [Mixtral 8x7B](https://noometry.com/models/mixtral-8x7b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 70.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 45 | [Gemini 1.0 Pro](https://noometry.com/models/gemini-1-0-pro) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 70% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 46 | [Llama 2-70B](https://noometry.com/models/llama-2-70b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 69.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 47 | [Command R+](https://noometry.com/models/command-r-plus) |  [![](/logos/cohere.svg) Cohere](https://noometry.com/providers/cohere) | 69.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 48 | [Llama 3-8B](https://noometry.com/models/llama-3-8b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 68.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 49 | [Phi 3 Mini 4k Instruct](https://noometry.com/models/phi-3-mini-4k-instruct) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 68.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 50 | [Mistral Small](https://noometry.com/models/mistral-small) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 68.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 51 | [Qwen1.5-14B](https://noometry.com/models/qwen1-5-14b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 68.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 52 | [Qwen2.5-Coder (1.5B)](https://noometry.com/models/qwen2-5-coder) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 68% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 53 | [Qwen-14B](https://noometry.com/models/qwen-14b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 66.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 54 | [Gemma 7B](https://noometry.com/models/gemma-7b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 66.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 55 | [Command R](https://noometry.com/models/command-r) |  [![](/logos/cohere.svg) Cohere](https://noometry.com/providers/cohere) | 65.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 56 | [StarCoder 2 15B](https://noometry.com/models/starcoder-2-15b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 64.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 57 | [Yi 6B](https://noometry.com/models/yi-6b) | [01.AI](https://noometry.com/providers/01-ai) | 64% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 58 | [Llama 2-34B](https://noometry.com/models/llama-2-34b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 62.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 59 | [Qwen1.5-7B](https://noometry.com/models/qwen1-5-7b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 62.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 60 | [Mistral 7B](https://noometry.com/models/mistral-7b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 62.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 61 | [Mistral 7B](https://noometry.com/models/mistral-7b) |  [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral) | 62.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 62 | [Nemotron-4 15B](https://noometry.com/models/nemotron-4-15b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 58.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 63 | [Falcon 2 11B](https://noometry.com/models/falcon-2-11b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 58.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 64 | [Phi-2](https://noometry.com/models/phi-2) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 58.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 65 | [Falcon-40B](https://noometry.com/models/falcon-40b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 56.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 66 | [Llama 3.2 11B](https://noometry.com/models/llama-3-2-11b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 56.5% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 67 | [Llama 3.1-8B](https://noometry.com/models/llama-3-1-8b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 56.1% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 68 | [Llama 2-13B](https://noometry.com/models/llama-2-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 55.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 69 | [INTELLECT-1](https://noometry.com/models/intellect-1) |  [![](/logos/huggingface.svg) Hugging Face](https://noometry.com/providers/huggingface) | 49.9% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 70 | [Llama 13b](https://noometry.com/models/llama-13b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 47.7% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 71 | [Llama 2-7B](https://noometry.com/models/llama-2-7b) |  [![](/logos/meta.svg) Meta](https://noometry.com/providers/meta) | 45.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 72 | [Qwen-7B](https://noometry.com/models/qwen-7b) |  [![](/logos/alibaba.svg) Alibaba (Qwen)](https://noometry.com/providers/alibaba) | 45% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 73 | [Gemma 2B](https://noometry.com/models/gemma-2b) |  [![](/logos/google.svg) Google](https://noometry.com/providers/google) | 42.3% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 74 | [DeepSeek Coder 33B](https://noometry.com/models/deepseek-coder-33b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 39.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 75 | [StarCoder 2 7B](https://noometry.com/models/starcoder-2-7b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 38.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 76 | [Phi-1.5](https://noometry.com/models/phi-1-5) |  [![](/logos/microsoft.svg) Microsoft](https://noometry.com/providers/microsoft) | 37.6% | 5 | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 77 | [StarCoder 2 3B](https://noometry.com/models/starcoder-2-3b) |  [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia) | 36.6% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 78 | [DeepSeek Coder 6.7B](https://noometry.com/models/deepseek-coder-6-7b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 36.4% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 79 | [Falcon-7B](https://noometry.com/models/falcon-7b) |  [![](/logos/tii.svg) Technology Innovation Institute](https://noometry.com/providers/tii) | 35% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 80 | [Dolly 2.0-12b](https://noometry.com/models/dolly-2-0-12b) |  [![](/logos/databricks.svg) Databricks](https://noometry.com/providers/databricks) | 26.2% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| 81 | [DeepSeek Coder 1.3B](https://noometry.com/models/deepseek-coder-1-3b) |  [![](/logos/deepseek.svg) DeepSeek](https://noometry.com/providers/deepseek) | 25.8% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

## Compare the leaders

-   [GPT-4o vs Claude 3.5 Sonnet](https://noometry.com/compare/claude-3-5-sonnet-vs-gpt-4o)
-   [GPT-4o vs DeepSeek-V3](https://noometry.com/compare/deepseek-v3-vs-gpt-4o)
-   [GPT-4o vs Gemini 1.5 Pro (May 2024)](https://noometry.com/compare/gemini-1-5-pro-vs-gpt-4o)
-   [GPT-4o vs GPT-4](https://noometry.com/compare/gpt-4-vs-gpt-4o)
-   [Claude 3.5 Sonnet vs DeepSeek-V3](https://noometry.com/compare/claude-3-5-sonnet-vs-deepseek-v3)
-   [Claude 3.5 Sonnet vs Gemini 1.5 Pro (May 2024)](https://noometry.com/compare/claude-3-5-sonnet-vs-gemini-1-5-pro)

## Other knowledge benchmarks

-   [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond)
-   [Humanity's Last Exam](https://noometry.com/benchmarks/hle)
-   [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified)
-   [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro)
-   [Confabulations](https://noometry.com/benchmarks/confabulations)
-   [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination)
-   [LMArena Expert](https://noometry.com/benchmarks/arena-expert)
-   [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa)
-   [ARC (AI2) Challenge](https://noometry.com/benchmarks/arc-challenge) (reference)
-   [BoolQ](https://noometry.com/benchmarks/boolq) (reference)
-   [OpenBookQA](https://noometry.com/benchmarks/openbookqa) (reference)
-   [TriviaQA](https://noometry.com/benchmarks/triviaqa) (reference)

## Frequently asked questions

### What does MMLU measure?

57-subject multiple-choice exam covering STEM, humanities and professional topics.

### Which model has the highest MMLU score?

As of October 2026, GPT-4o has the highest published MMLU score on Noometry at 88.1%, out of 81 models with results.

### What is the best open-weight model on MMLU?

DeepSeek-V3 has the highest MMLU accuracy among open-weight models at 87.2%, ranking 3 of 81 overall.

### Cite this page

Noometry. (2026). MMLU leaderboard. Retrieved October 10, 2026, from https://noometry.com/benchmarks/mmlu

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/benchmarks/mmlu.md).