LuminaBench
Anthropic / Published benchmarks

Claude 4.6 Opus

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

SWE-fficiency1,090Not specified · ExperimentalSWE-bench Multilingual — Original1,059Not specified · ExperimentalSWE-bench Verified — Original1,096Not specified · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

SWE-fficiency

SWE-fficiency

Version SWE-fficiency-498-Feb2026
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.

1 configuration · Publisher-run · Experimental conversion

1,090Best score · Not specified
Explore SWE-fficiency
SWE-bench Multilingual — Original

SWE-bench Multilingual — Original

Version SWE-bench-Multilingual-193160a463a4
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.

1 configuration · Publisher-run · Experimental conversion

1,059Best score · Not specified
Explore SWE-bench Multilingual — Original
SWE-bench Verified — Original

SWE-bench Verified — Original

Version SWE-bench-Verified-193160a463a4
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.

1 configuration · Publisher-run · Experimental conversion

1,096Best score · Not specified
Explore SWE-bench Verified — Original