Skip to content

Benchmark

VLMsAreBlind

Scores are percentages. Higher is better.

Models measured
6
Scores recorded
7
Sources
2
IQ weight
0.59

Score distribution

95.8%
Mean
96.9%
Median
1.8%
Std dev
93.1%
10th percentile
97%
90th percentile
93%
Min
93%97%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.59 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.5 35B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim97%
2Qwen3.6 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim97%
3Qwen3.6 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.97%
4Qwen3.5 27B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.9%
5Qwen3.5 122B-A10B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim96.7%
6Seed 2.0 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93.1%
7Doubao Seed 1.8· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim93%

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.