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
1Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91.3%
2Claude Opus 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim91%
3Qwen 3.8 Flash Next· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.6%
4Qwen3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.6%
5LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
6Qwen 3.8 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim90.2%
7Claude Opus 4.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.9%
8Gemini 3.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.4%
9GLM 5.3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89.4%
10Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim89%
11Gemini 3.7 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.7%
12Muse Spark 1.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.4%
13Claude Sonnet 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.3%
14Kimi K2.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.7%
15Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.4%
16Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.4%
17Gemini 3.8 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim86.2%
18Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.9%
19Inkling 2 Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim85.6%
20Gemini 3.5 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim84.2%
21Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.6%
22MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.5%
23GPT 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.1%
24GPT-5.5 Instant· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.6%
25Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.5%
26Gemini 3 Pro Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.4%
27GPT 5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.1%
28MiMo V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81%
29NVIDIA Nemotron 3.5 Super VL 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.8%
30Gemini 3 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.3%
31Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.5%
32Muse Glimmer 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.8%
33OpenAI o3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.6%
34Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.4%
35Inkling FP4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.1%
36Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
37Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.5%
38Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.5%
39Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.4%
40Inkling Small· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.4%
41Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim77.2%
42Gemini 3.5 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim76.5%
43Gemini 3.1 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.2%
44o4 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72%
45Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.4%
46Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.8%
47Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.66.1%
48Qwen3 VL 32B Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.65.2%
49Qwen3 VL 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62.8%
50Qwen3 VL 235B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62.1%

Showing 1–50 of 60 results.

Data credits: Data by LLM Stats