SWE-bench Multimodal · SWE-bench/experiments

Resolved-issue rate on JavaScript issues whose reports carry images, from the submission records behind the leaderboard.

ModelsModels with a result.7
Top resultBest result on this benchmark.36.0%o3
Top-3 spreadPoints from first to third.2.1 pts
UpdatedDate the source changed the results.17 Nov 2025

Result and price

6 of 7 results

Results

7 results
#ModelResultThe score from the source.
07GPT-4oRAG6.0%