Skip to content

Benchmark

SimpleVQA

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

Models measured
21
Scores recorded
25
Sources
2
IQ weight
0.07

Score distribution

26.9%
Mean
0.745%
Median
32.5%
Std dev
0.583%
10th percentile
71.2%
90th percentile
0.56%
Min
0.56%81.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.07 for chat models, measured over 21 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.7 PlusQwen3.7-Plus release · search augmentation enabled· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.81.7%
2Qwen3.8 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.75%
3Kimi K2.5setting not named by the source· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.2%
4Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.67.3%
5Qwen3.5 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.67.1%
6Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.4%
7Qwen3.5 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.65.3%
8Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.9%
9Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.56.1%
10Qwen3.5 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.54.4%
11Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.817%
12GLM 5V Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.782%
13Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.745%
14Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.736%
15Muse Spark· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.713%
16Kimi K2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.712%
17Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.711%
18Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.687%
19Qwen3.6 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.673%
20Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.617%
21Qwen3 VL 235Bthinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.0.613%
22Qwen3.6 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.589%
23Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.583%
24Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.561%
25Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim0.56%

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.