SWE-bench Verified — Original
Version SWE-bench-Verified-193160a463a42 configurations · Publisher-run · Experimental conversion
1,088Best score · Not specified
Explore SWE-bench Verified — Original Anthropic / Published benchmarks
Claude 4 Opus
Benchmark results and API pricing.
API pricing
USD / 1M tokensVerified pricing is unavailable for this model.
Lumina VerifiedLumina checked the published sources, versions, model labels, score extraction and conversion. External evaluations were run by their publishers; Lumina has not independently rerun or reproduced them.