Benchmark
CountQA
Vision benchmarks measure how well models understand images. Scores are percentages. Higher is better.
- Models measured
- 2
- Scores recorded
- 3
- Sources
- 2
- IQ weight
- No weight published
Score distribution
- 78.8%
- Mean
- 77%
- Median
- 2.5%
- Std dev
- 77%
- 10th percentile
- 82.4%
- 90th percentile
- 77%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3.8 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. | 82.4% |
| 2 | Qwen3.7 Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 77% |
| 3 | Qwen3.7 PlusQwen3.7-Plus release · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77% |
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. · Data by LLM Stats