Home/Browse/mmmu

mmmu

Unknown

mmmu is a state-of-the-art machine learning benchmark indexed on Codesota. This page tracks published model results, top scores per metric, and the SOTA timeline for mmmu.

Benchmark Stats

Models11
Papers11
Metrics1

SOTA History

Not enough data to show trend.

accuracy

Higher is better

RankModelSourceScoreYearPaper
1InternVL3-78B

MMMU val. InternVL3-78B. Table 2. arxiv:2501.12891

Community73.32026Source
2Gemini 2.0 Flash

MMMU val. Gemini 2.0 Flash. Technical report.

Community71.92026Source
3Qwen2.5-VL 72B

MMMU val. Qwen2.5-VL 72B. Table 2. arxiv:2502.13923

Community70.22026Source
4GPT-4o

MMMU val. GPT-4o system card Table 1. arxiv:2410.21276

Community69.12026Source
5Claude 3.5 Sonnet

MMMU val. Claude 3.5 Sonnet (Oct 2024). Anthropic model card.

Community68.32026Source
6InternVL2-76B

MMMU val. InternVL2-76B. Table 10. arxiv:2404.16821

Community67.42026Source
7Qwen2-VL 72B

MMMU val. Qwen2-VL 72B. Table 6. arxiv:2409.12191

Community64.52026Source
8Gemini 1.5 Pro

MMMU val. Table 5. Gemini 1.5 paper arxiv:2403.05530

Community62.22026Source
9Llama 3.2 Vision 90B

MMMU val. Llama 3.2 Vision 90B. Table 3. arxiv:2407.21783

Community60.32026Source
10Claude 3 Opus

MMMU val. 0-shot. Anthropic Claude 3 family model card. March 2024.

Community59.42026Source
11GPT-4V

MMMU val. 0-shot. MMMU benchmark paper Table 1. Source cross-referenced with GPT-4 Technical Report.

Community56.82026Source

Submit a Result