SWE-Bench.

SWE-bench is a full benchmark with diverse repositories that evaluates language models on software engineering tasks. Given a codebase and an issue, a language model is tasked with generating a patch that resolves the described problem. The full benchmark has 2,294 instances.

Best published scores.

No results indexed yet — be the first to submit a score.

Neighbouring benchmarks.

Other Few-Shot Image Classification datasets on Codesota.

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

• 01A public checkpoint or API endpoint
• 02A reproduction script with frozen commit + seed
• 03Declared evaluation environment (Python, deps)
• 04One row per metric declared by this dataset
• 05A contact so we can follow up on discrepancies