Skip to content

Benchmark

SWE-Review

Coding benchmarks compare models on programming tasks. Scores are percentages.

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

Score distribution

8.9%
Mean
8.9%
Median
0%
Std dev
8.9%
10th percentile
8.9%
90th percentile
8.9%
Min

Leaderboard

#ModelScore
1MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim8.9%

Data credits: Data by LLM Stats