Skip to content

Benchmark

LongAudioSpan · Chain

Scores are percentages. Higher is better.

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

Score distribution

52.6%
Mean
48.2%
Median
8.6%
Std dev
45.1%
10th percentile
64.6%
90th percentile
45.1%
Min
45.1%64.6%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemini 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.64.6%
2Qwen3.8 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.48.2%
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.45.1%

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.