llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeBenchmarksmultimodalPMC-VQA

multimodal benchmark

PMC-VQA

A medical visual question answering benchmark built on biomedical literature and medical figures.

Updated Aug 7, 2026

Published models3
Registry coverage3
MetricScore
EvidenceB

On this page

  • Ranking
  • Distribution
  • Highlights
  • About
  • FAQ

PMC-VQA leaderboard

Sorted by the source-provided rank. Higher score is better according to the registry.

3 rows
Columns

Show columns

1ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team63.3%100.0%3CAug 7, 2026
2ACQwen3.5-27BAlibaba Cloud / Qwen Team62.4%50.0%3CAug 7, 2026
3ACQwen3.5-35B-A3BAlibaba Cloud / Qwen Team62.0%0.0%3CAug 7, 2026

Score distribution

Top published rows on the benchmark's original scale.

PMC-VQA

PMC-VQA highlights

The top published results on this benchmark's own scale.

Rank #1Qwen3.5-122B-A10B63.3%Rank #2Qwen3.5-27B62.4%Rank #3Qwen3.5-35B-A3B62.0%

What is PMC-VQA?

Definition and scoring fields from the benchmark registry.

A medical visual question answering benchmark built on biomedical literature and medical figures.

Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.

Family
PMC-VQA
Modality
multimodal
Primary category
multimodal
Score direction
higher
LLMBoard eligible
No
Evaluation key
pmc-vqa|llm-stats-current

Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.

FAQ

Common questions about PMC-VQA.

Which model scores highest on PMC-VQA?

Qwen3.5-122B-A10B is currently ranked first with 63.3%.

What does PMC-VQA measure?

A medical visual question answering benchmark built on biomedical literature and medical figures.

Is a higher score better?

Yes. Higher values rank better for this benchmark.

How many models are compared?

3 unique published model results are currently shown.

Does this benchmark affect the overall score?

This benchmark is preserved as source-native evidence but is not eligible for the current overall score.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai