Search
Find recorded models, benchmarks, providers and individual results.
Filters: model:opus brand:claude benchmark:swe-bench record: metric:accuracy date:2026-09 org:anthropic
Enter a model, benchmark or provider name.
Find recorded models, benchmarks, providers and individual results.
Filters: model:opus brand:claude benchmark:swe-bench record: metric:accuracy date:2026-09 org:anthropic
Enter a model, benchmark or provider name.