CHAOS-Bench
The benchmark’s paper hasn’t scored a model released after GLM-OCR (January 2026). Labs report their own numbers for one newer model: MiniCPM-OCR-1.0 at 29.8%.
Models read deliberately corrupted words in 500 academic page images. Scores measure faithful recognition of the visible strings instead of correction to plausible words.
OpenBMB uses full-page matching and averages word-hit rates by page across 1,025 altered words. This differs from the maker protocol that aligns individual regions.
- Made by
- Tencent Hunyuan
- Released
- July 2026
- Kind
- Documents, charts and text in images
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
- Last in a launch post
- October 2026
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
MiniCPM-OCR-1.0 leads with 29.8%
Best score per model as labs report them in their own cards, drawn striped. Labs pick their own settings, so these compare less cleanly than independent runs.
DeepSeek-OCR 2 leads with 6.33% across all independent runs
Best score per model across the benchmark’s paper, Epoch AI’s own runs and any board Epoch AI copied. Dotted bars are reruns by Epoch AI or another board, and each row names its source.
MiniCPM-OCR-1.0 leads with 29.8%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 1
MiniCPM-OCR-1.0 29.8%
Source: Labs’ model cards
- 1
DeepSeek-OCR 2 6.33%
- 2 GLM-OCR 5.75%
Source: The CHAOS-Bench paper
- 1
MiniCPM-OCR-1.0 29.8%
- 2
DeepSeek-OCR 2 6.33%
- 3 GLM-OCR 5.75%
Sources: Labs’ model cards and the CHAOS-Bench paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 29.8% | Oct 2026 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 6.33% | Jan 2026 | Official leaderboard | ||
| 2 | GLM-OCR | 5.75% | Jan 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | 29.8% | Oct 2026 | Lab model card | ||
| 2 | 6.33% | Jan 2026 | Official leaderboard | ||
| 3 | GLM-OCR | 5.75% | Jan 2026 | Official leaderboard |
The benchmark's paper has 6 entries, 2 of them models we track. Switch the scores above to rank them together.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official CHAOS-Bench leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 28, 2026 | 29.8 | CHAOS-Bench |
More 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
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (6 entries) and launch posts (1 score).
- Pass Models scored 3 models we track, plus 4 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for MiniCPM-OCR-1.0.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 29.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 2 rows for models we track and 4 other entries at the last read.
- Pass Last read November 20th, 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.