MMMU-Pro leaderboard
As of 15 Nov 2026, the top score on MMMU-Pro is 89.3% by Gemini 4 Carbon (Google), ahead of Gemini 4 Argon at 88.3%, across 296 model configurations with a published result (Artificial Analysis, result dated 28 Oct 2026). MMMU-Pro is a harder version of the college-level multimodal exam MMMU: questions with images from science, engineering, medicine and the arts, with ten answer options and a vision-only variant where the question itself is inside the image. MMMU-Pro counts toward the BenchLeader multimodal score.
Key facts (as of 15 Nov 2026)
- Gemini 4 Carbon holds the top MMMU-Pro score at 89.3% (Artificial Analysis, 28 Oct 2026).
- Gemini 4 Argon is second on MMMU-Pro at 88.3% (Artificial Analysis, 30 Sep 2026).
- MMMU-Pro: College-level multimodal understanding. Run by Artificial Analysis (Artificial Analysis).
- 296 model configurations have a published MMMU-Pro result on BenchLeader (BenchLeader, 15 Nov 2026).
- MMMU-Pro feeds the multimodal category of the BenchLeader Index (BenchLeader methodology).
College-level multimodal understanding. Run by Artificial Analysis.
- Published by
- Artificial Analysis
- Category
- Multimodal
- Index weight
- 1.0
- Models
- 296
- Data as of
- 15 Nov 2026
Source: Artificial Analysis (artificialanalysis.ai). Data taken from the public leaderboard.
What the test looks like
MMMU-Pro is a harder version of the college-level multimodal exam MMMU: questions with images from science, engineering, medicine and the arts, with ten answer options and a vision-only variant where the question itself is inside the image.
How it is scored
Percent correct; Artificial Analysis runs the standard setting itself.
What to keep in mind
Requires vision, so text-only models are absent. Ten options make guessing less effective than on the original MMMU, so scores are lower.
- 1Gemini 4 Carbon (medium)89.3%
- 2Gemini 4 Argon (medium)88.3%
- 3Claude Opus 5.5 (max)87.7%
- 4GPT-6 Astra (max)86.9%
- 5Claude Opus 5.5 (xhigh)86.6%
- 6GPT-6 Astra (high)86.4%
- 7GPT-6 Astra (xhigh)86.2%
- 8GPT-6.1 Sol (max)86.0%
- 9Claude Opus 5.5 (high)85.8%
- 10Claude Opus 5.5 (medium)85.7%
- 11Gemini 3.8 Flash (high)85.6%
- 12Gemini 3.7 Flash (high)85.5%
- 13GPT-6 Astra (medium)85.1%
- 14GPT-6.1 Sol (xhigh)85.1%
- 15GPT-6.1 Sol (high)84.9%
| # | ||||
|---|---|---|---|---|
| 1 | 89.3% | 65.8 | 2026-10-28 | |
| 2 | 88.3% | 61.6 | 2026-09-30 | |
| 3 | 87.7% | 68.4 | 2026-09-22 | |
| 4 | 86.9% | 67.3 | 2026-09-03 | |
| 5 | 86.6% | 65.4 | 2026-09-22 | |
| 6 | 86.4% | 66.3 | 2026-09-03 | |
| 7 | 86.2% | 66.0 | 2026-09-03 | |
| 8 | 86.0% | 66.6 | 2026-09-29 | |
| 9 | 85.8% | 66.0 | 2026-09-22 | |
| 10 | 85.7% | 61.2 | 2026-09-22 | |
| 11 | 85.6% | 59.4 | 2026-09-02 | |
| 12 | 85.5% | 62.1 | 2026-08-13 | |
| 13 | 85.1% | 64.4 | 2026-09-03 | |
| 14 | 85.1% | 63.6 | 2026-09-29 | |
| 15 | 84.9% | 63.4 | 2026-09-29 | |
| 16 | 84.9% | 57.3 | 2026-08-13 | |
| 17 | 84.7% | 65.0 | 2026-07-24 | |
| 18 | 84.7% | 60.1 | 2026-08-13 | |
| 19 | 84.7% | 64.1 | 2026-10-26 | |
| 20 | 84.7% | 58.9 | 2026-09-22 | |
| 21 | 84.6% | 62.0 | 2026-09-03 | |
| 22 | 84.5% | 55.9 | 2026-09-02 | |
| 23 | 84.3% | 62.5 | 2026-05-19 | |
| 24 | 84.2% | 60.2 | 2026-09-02 | |
| 25 | 84.0% | 60.1 | 2026-07-24 | |
| 26 | 83.9% | 62.7 | 2026-09-29 | |
| 27 | 83.9% | 61.8 | 2026-10-23 | |
| 28 | 83.9% | 61.8 | 2026-05-19 | |
| 29 | 83.8% | 60.0 | 2026-10-26 | |
| 30 | 83.8% | 59.6 | 2026-10-26 | |
| 31 | 83.8% | 56.2 | 2026-10-12 | |
| 32 | 83.4% | 65.3 | 2026-07-09 | |
| 33 | 83.2% | 61.0 | 2026-07-21 | |
| 34 | 83.1% | 60.0 | 2026-09-29 | |
| 35 | 83.0% | 62.6 | 2026-09-22 | |
| 36 | 82.8% | 58.7 | 2026-09-02 | |
| 37 | 82.8% | 58.5 | 2026-10-26 | |
| 38 | 82.7% | 63.9 | 2026-07-09 | |
| 39 | 82.5% | 58.4 | 2026-09-22 | |
| 40 | 82.5% | 56.6 | 2026-10-26 | |
| 41 | 82.4% | 64.4 | 2026-07-24 | |
| 42 | 82.4% | 59.9 | 2026-02-19 | |
| 43 | 82.0% | 58.1 | 2026-09-02 | |
| 44 | 82.0% | 58.1 | 2026-09-22 | |
| 45 | 81.8% | 63.4 | 2026-07-09 | |
| 46 | 81.6% | 57.5 | 2026-07-24 | |
| 47 | 81.6% | 57.9 | 2026-11-05 | |
| 48 | 81.4% | 61.3 | 2026-07-09 | |
| 49 | 81.2% | 60.8 | 2026-04-23 | |
| 50 | 81.1% | 63.5 | 2026-04-23 | |
| 51 | 81.0% | 60.2 | 2026-07-09 | |
| 52 | 80.9% | 53.5 | 2026-10-15 | |
| 53 | 80.7% | 59.5 | 2026-07-09 | |
| 54 | 80.6% | 57.7 | 2026-10-17 | |
| 55 | 80.5% | 64.2 | 2026-04-08 | |
| 56 | 80.5% | 60.2 | 2026-07-16 | |
| 57 | 80.5% | 57.6 | 2026-06-01 | |
| 58 | 80.4% | 56.9 | 2026-09-22 | |
| 59 | 80.4% | 56.8 | 2026-07-08 | |
| 60 | 80.2% | 60.0 | 2025-11-18 |
Multimodal AI benchmark leaderboard · All LLM benchmarks
Related benchmarks
Top head-to-heads on MMMU-Pro
Cite as: BenchLeader, “MMMU-Pro leaderboard”, data as of 15 Nov 2026, https://www.benchleader.com/benchmarks/aa_mmmu_pro.
MMMU-Pro: questions
- What does MMMU-Pro measure?
- MMMU-Pro is a harder version of the college-level multimodal exam MMMU: questions with images from science, engineering, medicine and the arts, with ten answer options and a vision-only variant where the question itself is inside the image. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on MMMU-Pro?
- As of 15 Nov 2026, the highest score on MMMU-Pro is 89.3% by Gemini 4 Carbon (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 88.3%. Scores come from Artificial Analysis and are re-read daily.
- Which AI model leads MMMU-Pro?
- Gemini 4 Carbon leads MMMU-Pro with 89.3% as of 15 Nov 2026 (result dated 28 Oct 2026), ahead of Gemini 4 Argon at 88.3%.
- How many models have MMMU-Pro results?
- 296 model configurations have a MMMU-Pro result on BenchLeader, all taken from Artificial Analysis.
- Who runs MMMU-Pro and how often is it updated?
- MMMU-Pro is published by Artificial Analysis. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does MMMU-Pro count toward the BenchLeader Index?
- Yes. MMMU-Pro contributes to the multimodal category of the BenchLeader Index, normalised so that 50 is the average of the evaluated models.