BlogLLM Benchmark Scores as Published, Side by Side
PMC-VQA: Results as Published
Every result the catalog holds for PMC-VQA: 11 models from 5 developers, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area HealthcareMaintainer Xiaoman Zhang, Chaoyi Wu, Ziheng Zhao, Weixiong Lin, Ya Zhang, Yanfeng Wang, and Weidi Xie (Shanghai Jiao Tong University and Shanghai AI Laboratory)Introduced 2023Data version 2026103001, as of 2026-10-30
PMC-VQA is a medical visual question answering set built from PubMed Central figures. It contains 227k question-answer pairs over 149k images covering many modalities and diseases. The authors treat the main task as free-form generation, and they also score a manually checked test split both as multiple choice and as open-ended blanking. Choice is scored by accuracy, and blanking is scored by accuracy and BLEU-1.
PMC-VQA
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5.2OpenAI, released 2025-12-11 | 58.9% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| GPT-5 miniOpenAI, released 2025-08-07 | 36.3% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Claude Opus 4.5Anthropic, released 2025-11-24 | 59.9% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Claude Sonnet 4.5Anthropic, released 2025-09-29 | 55.9% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Gemini 3 ProGoogle, released 2025-11-18 | 62.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3.5-122B-A10BAlibaba, released 2026-02-24 | 63.3% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-27BAlibaba, released 2026-02-24 | 62.4% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-35B-A3BAlibaba, released 2026-02-24 | 62% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15 | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 64.2% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
| Qwen3-VL-235B-A22BAlibaba, released 2025-09-23 | 41.2% | Alibaba, Qwen3.5-122B-A10B model cardchecked 2026-10-15; printed on 1 more page | - |
| Kimi K2.5Moonshot AI, released 2026-01-27 | 63.3% | Alibaba, Qwen3.5-397B-A17B model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.