Skip to content

Benchmark

PMC-VQA

Vision benchmarks measure how well models understand images. Scores are percentages. Higher is better.

Models measured
7
Scores recorded
7
Sources
2
IQ weight
0.62

Score distribution

62.8%
Mean
62.7%
Median
2.1%
Std dev
62%
10th percentile
64.2%
90th percentile
58.7%
Min
58.7%66.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.62 for chat models, measured over 7 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66.2%
2Qwen3.5 397B A17BQwen3.5 release/model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.64.2%
3Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.3%
4Qwen3.5 Omni PlusQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.62.7%
5Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.4%
6Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62%
7Qwen3.5 Omni FlashQwen3.5-Omni release · published setting· Reported by Qwen, Qwen Team· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.7%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.