Skip to content

Benchmark

Arena-Hard · Hard Prompt

People compare model answers and choose which they prefer. Scores are percentages. Higher is better.

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

Score distribution

54.1%
Mean
54.1%
Median
0%
Std dev
54.1%
10th percentile
54.1%
90th percentile
54.1%
Min

Leaderboard

#ModelScore
1MiMo V2 FlashMiMo-V2-Flash final evaluation · Hard Prompt· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.1%

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.