EXAMS-V
Models answer multilingual school examination questions presented as images. Questions can require reading diagrams, maps, tables, or formulas.
- Made by
- Rocktim Jyoti Das and colleagues
- Released
- March 2024
- Kind
- Knowledge in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics, Physical sciences, Chemical sciences, Biological sciences, Social and economic geography
- Language
- Many languages
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- January 2024
- Scores refreshed
- November 20th, 2026
GPT-4 (snapshot unspecified) tops the leaderboard with 47.1% Gemini 1.0 Pro leads with 44% among models released by January 2024
Best score per entry from the benchmark's paper, read on November 20th, 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. The best model we track is Gemini 1.0 Pro, at 44%. This view shows only models we track, each at its best.
The newest model with a score here came out in January 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4 (snapshot unspecified) OCR and captioning 47.1%
- 2
Gemini 1.0 Pro OCR and captioning 44%
- 3 GPT-4V Image input 42.8%
- 4 GPT-3.5 Turbo (snapshot unspecified) OCR and captioning 39.5%
- 5
Gemini 1.0 Pro Vision Image input 31.1%
Source: The EXAMS-V paper
- 1
Gemini 1.0 Pro OCR and captioning 44%
- 2 GPT-4V Image input 42.8%
- 3
Gemini 1.0 Pro Vision Image input 31.1%
Source: The EXAMS-V paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 (snapshot unspecified) | 47.1% | OCR and captioning | Official leaderboard | |
| 2 | | 44% | OCR and captioning | Dec 2023 | Official leaderboard |
| 3 | GPT-4V | 42.8% | Image input | Nov 2023 | Official leaderboard |
| 4 | GPT-3.5 Turbo (snapshot unspecified) | 39.5% | OCR and captioning | Official leaderboard | |
| 5 | | 31.1% | Image input | Jan 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 44% | OCR and captioning | Dec 2023 | Official leaderboard |
| 2 | GPT-4V | 42.8% | Image input | Nov 2023 | Official leaderboard |
| 3 | | 31.1% | Image input | Jan 2024 | Official leaderboard |
Rankings by part
We read 11 parts from the benchmark’s paper, each ranking models on one part of the test, such as Bulgarian, Chinese and Croatian. GPT-4V leads 5 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Bulgarian
3 models we track have a score here.
- 1 GPT-4V ↑1 36%
- 2
Gemini 1.0 Pro ↓1 32%
- 3
Gemini 1.0 Pro Vision 30.5%
Chinese
3 models we track have a score here.
- 1
Gemini 1.0 Pro Vision ↑2 24.6%
- 2
Gemini 1.0 Pro ↓1 24%
- 3 GPT-4V ↓1 22.2%
Croatian
3 models we track have a score here.
- 1
Gemini 1.0 Pro 58.9%
- 2 GPT-4V 55.5%
- 3
Gemini 1.0 Pro Vision 29.4%
French
3 models we track have a score here.
- 1 GPT-4V ↑1 60.3%
- 2
Gemini 1.0 Pro Vision ↑1 47.7%
- 3
Gemini 1.0 Pro ↓2 38.5%
German
3 models we track have a score here.
- 1 GPT-4V ↑1 51.2%
- 2
Gemini 1.0 Pro Vision ↑1 47.8%
- 3
Gemini 1.0 Pro ↓2 28.1%
Hungarian
3 models we track have a score here.
- 1 GPT-4V ↑1 44.8%
- 2
Gemini 1.0 Pro ↓1 43.4%
- 3
Gemini 1.0 Pro Vision 27.1%
English
3 models we track have a score here.
- 1
Gemini 1.0 Pro 31.2%
- 2 GPT-4V 29.3%
- 3
Gemini 1.0 Pro Vision 29.2%
Serbian
3 models we track have a score here.
- 1
Gemini 1.0 Pro 60%
- 2 GPT-4V 39.8%
- 3
Gemini 1.0 Pro Vision 28.3%
Italian
3 models we track have a score here.
- 1
Gemini 1.0 Pro 64.4%
- 2 GPT-4V 62.1%
- 3
Gemini 1.0 Pro Vision 43%
Arabic
3 models we track have a score here.
- 1 GPT-4V ↑1 24.3%
- 2
Gemini 1.0 Pro ↓1 23.3%
- 3
Gemini 1.0 Pro Vision 19.4%
Polish
3 models we track have a score here.
- 1
Gemini 1.0 Pro 42%
- 2 GPT-4V 30%
- 3
Gemini 1.0 Pro Vision 28%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The EXAMS-V paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official EXAMS-V 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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in January 2024, for Gemini 1.0 Pro Vision. 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 (5 entries).
- Pass Models scored 3 models we track, plus 2 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in January 2024, for Gemini 1.0 Pro Vision.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 44%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track and 2 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.