image to text benchmark
OCRBench_V2 Leaderboard
OCRBench v2: Enhanced large-scale bilingual benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with 10,000 human-verified question-answering pairs across 8 core OCR capabilities
Updated Aug 17, 2026
Models7
Model coverage7
MetricScore
EvidenceB
OCRBench_V2 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score67.1% | Percentile100.0% | Participants7 | EvidenceC | Evaluated |
| Rank02 | ModelAM Nova 2 ProAmazon | Score64.5% | Percentile83.3% | Participants7 | EvidenceC | Evaluated |
| Rank03 | ModelBY | Score63.2% | Percentile66.7% | Participants7 | EvidenceC | Evaluated |
| Rank04 | ModelBY | Score62.8% | Percentile50.0% | Participants7 | EvidenceC | Evaluated |
| Rank05 | ModelAMNova 2 OmniAmazon | Score58.2% | Percentile33.3% | Participants7 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score57.8% | Percentile16.7% | Participants7 | EvidenceC | Evaluated |
| Rank07 | ModelAMNova 2 LiteAmazon | Score56.1% | Percentile0.0% | Participants7 | EvidenceC | Evaluated |
OCRBench_V2 Highlights
The leading models and scores on this benchmark.
OCRBench_V2 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for OCRBench_V2
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis ocrbench_v2 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 67.1%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #1 of 7 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures OCRBench_V2, not total model capability
- 02AMNova 2 ProAmazon
- Score
- 64.5%
Strengths
- Ranks #2 of 7 compared models
- 83th percentile on this benchmark
- C evidence result
Considerations
- This result measures OCRBench_V2, not total model capability
- 03BYSeed 2.1 ProByteDance
- Score
- 63.2%
Strengths
- Ranks #3 of 7 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures OCRBench_V2, not total model capability
- 04BYSeed 2.1 TurboByteDance
- Score
- 62.8%
Strengths
- Ranks #4 of 7 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures OCRBench_V2, not total model capability
- 05AMNova 2 OmniAmazon
- Score
- 58.2%
Strengths
- Ranks #5 of 7 compared models
- 33th percentile on this benchmark
- C evidence result
Considerations
- This result measures OCRBench_V2, not total model capability
Selection summary
Best AI Models for OCRBench_V2
Qwen3.7-Plus currently leads OCRBench_V2 with 67.1%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is OCRBench_V2?
What OCRBench_V2 measures and how its scores work.
OCRBench v2: Enhanced large-scale bilingual benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with 10,000 human-verified question-answering pairs across 8 core OCR capabilities
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- OCRBench_V2
- Modality
- multimodal
- Primary category
- image to text
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- ocrbench-v2|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about OCRBench_V2.
Which model scores highest on OCRBench_V2?
Qwen3.7-Plus is currently ranked first with 67.1%.
What does OCRBench_V2 measure?
OCRBench v2: Enhanced large-scale bilingual benchmark for evaluating Large Multimodal Models on visual text localization and reasoning with 10,000 human-verified question-answering pairs across 8 core OCR capabilities
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
7 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.