Skip to content

Benchmark

CharXiv-R

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

Models measured
58
Scores recorded
60
Sources
1
IQ weight
2.57

Score distribution

76.5%
Mean
80.3%
Median
12.9%
Std dev
56.6%
10th percentile
89.9%
90th percentile
40.5%
Min
40.5%91.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.57 for chat models, measured over 58 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim58.8%
52GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.8%
53GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.7%
54qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.56.6%
55GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.4%
56Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.53%
57Command A Plus 05 2026· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim52.7%
58qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.48.9%
59Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.46.4%
60GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim40.5%

Showing 51–60 of 60 results.

Data credits: Data by LLM Stats