Skip to content

Benchmark

LongAudioSpan · Rubric

Scores are percentages. Higher is better.

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

Score distribution

62.4%
Mean
65.5%
Median
9.3%
Std dev
49.8%
10th percentile
71.8%
90th percentile
49.8%
Min
49.8%71.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen3.8 Omni FlashQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.8%
2Gemini 3.8 FlashQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.65.5%
3Qwen3.5 Omni PlusQwen3.8 Omni Flash 官方发布表· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.49.8%

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.