Benchmark Almanac

MMK12

o1 73.9% leads since April 2025
Not in model cards

Models use images to answer school mathematics and science questions. The test split contains 2,000 problems with reference answers.

The authors publish separate subject scores for open and proprietary models. Prime Intellect provides an independent evaluation environment.

Made by
MM-EUREKA team
Released
April 2025
Kind
Visual math and diagrams
Level
School
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Items from
Exams and contests
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
o1 #118 on the capability index
Last model added
March 2025
Scores refreshed
November 21st, 2026
18
Entries in its paper, 10 models we track

o1 leads with 73.9% among models released by March 2025 o1 leads with 73.9% among models released by March 2025

Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

The newest model with a score here came out in March 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 o1 73.9%
  2. 2 MM-Eureka-32B 72.2%
  3. 3 Qwen2.5-VL-72B 70.5%
  4. 4 Qwen2.5-VL-32B 66.8%
  5. 5 Gemini 2.0 Flash Feb 2025 65.2%
  6. 6 MM-Eureka-7B 64.5%
  7. 7 InternVL2.5-VL-78B 61.6%
  8. 8 QVQ-72B-Preview 61.5%
  9. 9 OpenVLThinker-7 60.6%
  10. 10 Adora 58.1%
  11. 11 InternVL2.5-VL-38B 58%
  12. 12 Claude 3.7 Sonnet 55.3%
  13. 13 Qwen2.5-VL-7B 53.6%
  14. 14 GPT-4o Mar 2025 49.9%
  15. 15 InternVL2.5-38B-MPO 48.3%
  16. 16 InternVL2.5-VL-8B 45.6%
  17. 17 R1-Onevision 39.8%
  18. 18 InternVL2.5-8B-MPO 34.5%

Source: The MMK12 paper

#EntryScoreSettingDateSource
1 o1 73.9% Dec 2024 Official leaderboard
2 MM-Eureka-32B 72.2% Official leaderboard
3 Qwen2.5-VL-72B 70.5% Jan 2025 Official leaderboard
4 Qwen2.5-VL-32B 66.8% Mar 2025 Official leaderboard
5 Gemini 2.0 Flash Feb 2025 65.2% Feb 2025 Official leaderboard
6 MM-Eureka-7B 64.5% Official leaderboard
7 InternVL2.5-VL-78B 61.6% Official leaderboard
8 QVQ-72B-Preview 61.5% Dec 2024 Official leaderboard
9 OpenVLThinker-7 60.6% Official leaderboard
10 Adora 58.1% Official leaderboard
11 InternVL2.5-VL-38B 58% Official leaderboard
12 Claude 3.7 Sonnet 55.3% Feb 2025 Official leaderboard
13 Qwen2.5-VL-7B 53.6% Jan 2025 Official leaderboard
14 GPT-4o Mar 2025 49.9% Mar 2025 Official leaderboard
15 InternVL2.5-38B-MPO 48.3% Dec 2024 Official leaderboard
16 InternVL2.5-VL-8B 45.6% Official leaderboard
17 R1-Onevision 39.8% Official leaderboard
18 InternVL2.5-8B-MPO 34.5% Dec 2024 Official leaderboard
#ModelScoreSettingDateSource
1 o1 73.9% Dec 2024 Official leaderboard
2 Qwen2.5-VL-72B 70.5% Jan 2025 Official leaderboard
3 Qwen2.5-VL-32B 66.8% Mar 2025 Official leaderboard
4 Gemini 2.0 Flash Feb 2025 65.2% Feb 2025 Official leaderboard
5 QVQ-72B-Preview 61.5% Dec 2024 Official leaderboard
6 Claude 3.7 Sonnet 55.3% Feb 2025 Official leaderboard
7 Qwen2.5-VL-7B 53.6% Jan 2025 Official leaderboard
8 GPT-4o Mar 2025 49.9% Mar 2025 Official leaderboard
9 InternVL2.5-38B-MPO 48.3% Dec 2024 Official leaderboard
10 InternVL2.5-8B-MPO 34.5% Dec 2024 Official leaderboard

Rankings by part

We read 4 parts from the benchmark’s paper, each ranking models on one part of the test, such as Mathematics, Physics and Chemistry. o1 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Mathematics

10 models we track have a score here.

  1. 1 o1 81.6%
  2. 2 Gemini 2.0 Flash Feb 2025 ↑2 76.8%
  3. 3 Qwen2.5-VL-72B ↓1 75.6%
  4. 4 Qwen2.5-VL-32B ↓1 71.6%
  5. 5 QVQ-72B-Preview 61.4%
  6. 6 Qwen2.5-VL-7B ↑1 58.4%
  7. 7 Claude 3.7 Sonnet ↓1 57.4%
  8. 8 GPT-4o Mar 2025 55.8%
  9. 9 InternVL2.5-38B-MPO 41.4%
  10. 10 InternVL2.5-8B-MPO 26.6%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper Not tested since Apr 2025
o1 73.9%

Source: The MMK12 paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o1 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) o1

Source: Official MMK12 leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 20 months ago, in March 2025, for GPT-4o. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (18 entries).
  • Pass Models scored 10 models we track, plus 8 other entries on its leaderboard.
  • Warning Newest score The newest came 20 months ago, in March 2025, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is o1 (#118).
  • Pass Headroom The best is 73.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 10 rows for models we track and 8 other entries at the last read.
  • Pass Last read November 21st, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check