Skip to content

Benchmark

CharXiv-D

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

Models measured
14
Scores recorded
15
Sources
1
IQ weight
2.27

Score distribution

87.8%
Mean
88%
Median
5%
Std dev
83%
10th percentile
94.6%
90th percentile
73.9%
Min
73.9%95.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.27 for chat models, measured over 14 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim95.5%
2Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim94.6%
3Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.9%
4Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.90.5%
5Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.90.2%
6GPT-4.5 Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90%
7GPT-4.1 mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.4%
8Command A Plus 05 2026· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88%
9GPT 4.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.9%
10qwen3-vl-30bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.86.9%
11Qwen: Qwen3 VL 8B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85.9%
12qwen3-vl-30b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.85.5%
13GPT 4o· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.3%
14Qwen3 VL 8B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83%
15GPT-4.1 nano· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.9%

Data credits: Data by LLM Stats