Skip to content

Benchmark

RecreationBench · Qwen release metric (unspecified)

Scores are percentages. Higher is better.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

49.6%
Mean
49.9%
Median
1.9%
Std dev
47.1%
10th percentile
51.7%
90th percentile
47.1%
Min
47.1%51.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.8 MaxQwen3.8-Max release vision/video table · internal benchmark · Ubuntu/macOS/Windows/Android/web· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.51.7%
2Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · internal benchmark · Ubuntu/macOS/Windows/Android/web· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.9%
3Qwen 3.8 27BQwen3.8-27B model card · internal benchmark · Ubuntu/macOS/Windows/Android/web· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.47.1%

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.