Skip to content

Benchmark

MiMo Coding Bench

Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.

Models measured
4
Scores recorded
6
Sources
2
IQ weight
No weight published

Score distribution

69.2%
Mean
71.8%
Median
5.1%
Std dev
63.2%
10th percentile
73.7%
90th percentile
61.2%
Min
61.2%73.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1MiMo V2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.7%
2MiMo V2.5 ProXiaomi MiMo-V2.5-Pro official launch table · Xiaomi internal coding-agent evaluation · frameworks such as Claude Code· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.73.7%
3MiMo V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.8%
4MiMo V2.5Xiaomi MiMo-V2.5 official release/model card · Xiaomi internal coding-agent evaluation· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.71.8%
5MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.2%
6MiMo V2.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.2%

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