Skip to content

Benchmark

CharXiv (RQ) · With CI

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

Models measured
8
Scores recorded
10
Sources
1
IQ weight
1.77

Score distribution

89.6%
Mean
90.6%
Median
2.4%
Std dev
85.9%
10th percentile
91.4%
90th percentile
85.9%
Min
85.9%93.5%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.77 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · with Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.5%
2Qwen3.8 Omni FlashRQ · With Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.4%
3Kimi K3Python tool · three-run average · max effort· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.3%
4Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · with Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.6%
5Qwen3.8 FlashRQ · With Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.6%
6Qwen 3.8 27BQwen3.8-27B model card · with Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.2%
7Qwen 3.8 27BRQ · With Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.90.2%
8Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · RQ · with Python · max 50 steps · avg@3· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.7%
9Qwen3.7 PlusQwen3.7-Plus release · with Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.9%
10Qwen3.7 PlusRQ · With Code Interpreter· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.9%

Data credits: 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.