Mini Swe Agent Bench
Frontier
Benchmarking model performance on SWE Bench in the Mini SWE Agent harness.
- Domain
- rl-env
- License
- unknown
- Published
- Mar 2026
Cite
Notes
Only stored in your browser.
Top score 93.3% by GPT-5 - 3 models reporting (3 frontier)
Score history
3Top models
3
Related tools
1Implementations, trainers, datasets and scaffolds linked to this eval.
FAQ
- What is Mini Swe Agent Bench?
- Benchmarking model performance on SWE Bench in the Mini SWE Agent harness.
- What is the current top score on Mini Swe Agent Bench?
- The top reported score is 93.3% by GPT-5, across 3 models reporting (3 from frontier labs).
- How can a model improve its Mini Swe Agent Bench score?
- Tools linked to Mini Swe Agent Bench on Sophon include Agent Bench RL Env (Prime Community) - RL environments, datasets, and scaffolds that target this eval.
- What license is Mini Swe Agent Bench under?
- Mini Swe Agent Bench is available under unknown.