SWT-Bench
Progress Over Time
Interactive timeline showing model performance evolution on SWT-Bench
State-of-the-art frontier
Open
Proprietary
SWT-Bench Leaderboard
1 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  MiniMax | 230B | 1.0M | $0.30 / $1.20 |
Notice missing or incorrect data?
What is SWT-Bench?
Software Test Benchmark evaluating LLM ability to write tests for software repositories
SWT-Bench is a text benchmark evaluating models on code tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.7, with the leader at 0.7.
Compare leaders on the best AI for code leaderboards.
Current leaders
MiniMax M2.1 from MiniMax currently leads the SWT-Bench leaderboard with a score of 0.693 across 1 evaluated AI models.
FAQ
Common questions about the SWT-Bench benchmark and leaderboard.