LiveOCRVQA
Models read stylized text in images and answer questions about it.
The publisher reports model results.
- Made by
- BAAI FlagEval
- Kind
- Documents, charts and text in images
- Level
- Everyday
- 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
- Strongest model tested
-
Gemini 2.5 Pro Jun 2025 #97 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
Gemini 2.5 Pro leads with 80.5 among models released by September 2025 Gemini 2.5 Pro leads with 80.5 among models released by September 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 September 2025, 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
- 80.5
Gemini 2.5 Pro
- 75.3
Gemini 2.5 Flash
- 72.2 Qwen2-VL-7B-Instruct
- 69.1 GPT-4o-2411
- 67.5 GPT-4o mini
- 67.3
Qwen2.5-VL-72B
- 67.0 GPT-4o-2408
- 66.0
Qwen2.5-VL-7B
- 64.7
Qwen2-VL-2B-Instruct
- 63.6 Qwen2-VL-72B
- 63.6
InternVL3-78B
- 62.6 Claude 3.7 Sonnet
- 59.7 Claude 3.5 Sonnet
- 59.0
Pixtral Large
- 50.6
InternVL2_5-78B
- 49.6
InternVL3-8B
- 45.7
LLaVA-OneVision 7B
- 39.2
InternVL2.5-8B
- 37.4 Phi-3.5-vision-instruct
- 28.1
Idefics3-8B-Llama3
- 17.9
Phi-4-multimodal
- 1
Gemini 2.5 Pro Jun 2025 80.5
- 2
Gemini 2.5 Flash Sep 2025 75.3
- 3 Qwen2-VL-7B-Instruct 72.2
- 4 GPT-4o-2411 69.1
- 5 GPT-4o mini 67.5
- 6
Qwen2.5-VL-72B 67.3
- 7 GPT-4o-2408 67.0
- 8
Qwen2.5-VL-7B 66.0
- 9
Qwen2-VL-2B-Instruct 64.7
- 10 Qwen2-VL-72B 63.6
- 11
InternVL3-78B 63.6
- 12 Claude 3.7 Sonnet 62.6
- 13 Claude 3.5 Sonnet 59.7
- 14
Pixtral Large 59.0
- 15
InternVL2_5-78B 50.6
- 16
InternVL3-8B 49.6
- 17
LLaVA-OneVision 7B 45.7
- 18
InternVL2.5-8B 39.2
- 19 Phi-3.5-vision-instruct 37.4
- 20
Idefics3-8B-Llama3 28.1
- 21
Phi-4-multimodal 17.9
Source: Official LiveOCRVQA leaderboard
- 80.5
Gemini 2.5 Pro
- 75.3
Gemini 2.5 Flash
- 72.2 Qwen2-VL-7B-Instruct
- 67.5 GPT-4o mini
- 67.3
Qwen2.5-VL-72B
- 66.0
Qwen2.5-VL-7B
- 64.7
Qwen2-VL-2B-Instruct
- 63.6
InternVL3-78B
- 62.6 Claude 3.7 Sonnet
- 59.7 Claude 3.5 Sonnet
- 59.0
Pixtral Large
- 50.6
InternVL2_5-78B
- 49.6
InternVL3-8B
- 45.7
LLaVA-OneVision 7B
- 39.2
InternVL2.5-8B
- 37.4 Phi-3.5-vision-instruct
- 28.1
Idefics3-8B-Llama3
- 17.9
Phi-4-multimodal
- 1
Gemini 2.5 Pro Jun 2025 80.5
- 2
Gemini 2.5 Flash Sep 2025 75.3
- 3 Qwen2-VL-7B-Instruct 72.2
- 4 GPT-4o mini 67.5
- 5
Qwen2.5-VL-72B 67.3
- 6
Qwen2.5-VL-7B 66.0
- 7
Qwen2-VL-2B-Instruct 64.7
- 8
InternVL3-78B 63.6
- 9 Claude 3.7 Sonnet 62.6
- 10 Claude 3.5 Sonnet 59.7
- 11
Pixtral Large 59.0
- 12
InternVL2_5-78B 50.6
- 13
InternVL3-8B 49.6
- 14
LLaVA-OneVision 7B 45.7
- 15
InternVL2.5-8B 39.2
- 16 Phi-3.5-vision-instruct 37.4
- 17
Idefics3-8B-Llama3 28.1
- 18
Phi-4-multimodal 17.9
Source: Official LiveOCRVQA leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 80.5 | Jun 2025 | Official leaderboard | |
| 2 | | 75.3 | Sep 2025 | Official leaderboard | |
| 3 | Qwen2-VL-7B-Instruct | 72.2 | Aug 2024 | Official leaderboard | |
| 4 | GPT-4o-2411 | 69.1 | Official leaderboard | ||
| 5 | GPT-4o mini | 67.5 | Jul 2024 | Official leaderboard | |
| 6 | | 67.3 | Jan 2025 | Official leaderboard | |
| 7 | GPT-4o-2408 | 67.0 | Official leaderboard | ||
| 8 | | 66.0 | Jan 2025 | Official leaderboard | |
| 9 | | 64.7 | Aug 2024 | Official leaderboard | |
| 10 | Qwen2-VL-72B | 63.6 | Official leaderboard | ||
| 11 | | 63.6 | Apr 2025 | Official leaderboard | |
| 12 | Claude 3.7 Sonnet | 62.6 | Feb 2025 | Official leaderboard | |
| 13 | Claude 3.5 Sonnet | 59.7 | Jun 2024 | Official leaderboard | |
| 14 | | 59.0 | Nov 2024 | Official leaderboard | |
| 15 | | 50.6 | Dec 2024 | Official leaderboard | |
| 16 | | 49.6 | Apr 2025 | Official leaderboard | |
| 17 | | 45.7 | Aug 2024 | Official leaderboard | |
| 18 | | 39.2 | Dec 2024 | Official leaderboard | |
| 19 | Phi-3.5-vision-instruct | 37.4 | Aug 2024 | Official leaderboard | |
| 20 | | 28.1 | Aug 2024 | Official leaderboard | |
| 21 | | 17.9 | Feb 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 80.5 | Jun 2025 | Official leaderboard | |
| 2 | | 75.3 | Sep 2025 | Official leaderboard | |
| 3 | Qwen2-VL-7B-Instruct | 72.2 | Aug 2024 | Official leaderboard | |
| 4 | GPT-4o mini | 67.5 | Jul 2024 | Official leaderboard | |
| 5 | | 67.3 | Jan 2025 | Official leaderboard | |
| 6 | | 66.0 | Jan 2025 | Official leaderboard | |
| 7 | | 64.7 | Aug 2024 | Official leaderboard | |
| 8 | | 63.6 | Apr 2025 | Official leaderboard | |
| 9 | Claude 3.7 Sonnet | 62.6 | Feb 2025 | Official leaderboard | |
| 10 | Claude 3.5 Sonnet | 59.7 | Jun 2024 | Official leaderboard | |
| 11 | | 59.0 | Nov 2024 | Official leaderboard | |
| 12 | | 50.6 | Dec 2024 | Official leaderboard | |
| 13 | | 49.6 | Apr 2025 | Official leaderboard | |
| 14 | | 45.7 | Aug 2024 | Official leaderboard | |
| 15 | | 39.2 | Dec 2024 | Official leaderboard | |
| 16 | Phi-3.5-vision-instruct | 37.4 | Aug 2024 | Official leaderboard | |
| 17 | | 28.1 | Aug 2024 | Official leaderboard | |
| 18 | | 17.9 | Feb 2025 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Album, Book and Game. Gemini 2.5 Pro leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Album
18 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 68.3
- 2
Gemini 2.5 Flash Sep 2025 66.2
- 3 Qwen2-VL-7B-Instruct 64.1
- 4 GPT-4o mini 54.9
- 5
InternVL3-78B ↑3 54.2
- 6
Qwen2.5-VL-72B ↓1 53.5
- 7
Qwen2-VL-2B-Instruct 52.8
- 8
Qwen2.5-VL-7B ↓2 51.4
- 9
LLaVA-OneVision 7B ↑5 45.8
- 10
InternVL2_5-78B ↑2 43.7
Book
18 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 90.1
- 2 Claude 3.7 Sonnet ↑7 85.9
- 3 GPT-4o mini ↑1 83.1
- 4 Qwen2-VL-7B-Instruct ↓1 83.1
- 5
Gemini 2.5 Flash Sep 2025 ↓3 80.3
- 6 Claude 3.5 Sonnet ↑4 76.1
- 7
Qwen2-VL-2B-Instruct 76.1
- 8
Pixtral Large ↑3 76.1
- 9
Qwen2.5-VL-7B ↓3 74.7
- 10
Qwen2.5-VL-72B ↓5 71.8
Game
18 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 85.7
- 2
Gemini 2.5 Flash Sep 2025 81.3
- 3
Qwen2.5-VL-72B ↑2 75.0
- 4
Qwen2.5-VL-7B ↑2 72.3
- 5 Qwen2-VL-7B-Instruct ↓2 71.4
- 6 GPT-4o mini ↓2 70.5
- 7
InternVL3-78B ↑1 68.8
- 8
Qwen2-VL-2B-Instruct ↓1 66.1
- 9 Claude 3.7 Sonnet 66.1
- 10 Claude 3.5 Sonnet 62.5
Movie
18 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 88.3
- 2 Claude 3.7 Sonnet ↑7 86.7
- 3 Claude 3.5 Sonnet ↑7 83.3
- 4 Qwen2-VL-7B-Instruct ↓1 80.0
- 5
Qwen2.5-VL-72B 80.0
- 6
Gemini 2.5 Flash Sep 2025 ↓4 80.0
- 7
Qwen2.5-VL-7B ↓1 78.3
- 8
Qwen2-VL-2B-Instruct ↓1 76.7
- 9
Pixtral Large ↑2 76.7
- 10 GPT-4o mini ↓6 73.3
4 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official LiveOCRVQA leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official LiveOCRVQA 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
- 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (21 entries).
- Pass Models scored 18 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Pro (#97).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on flageval-baai.github.io: 18 rows for models we track and 3 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.