LuminaBench
Anthropic / Published benchmarks

Claude 3.5 Sonnet

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

SWE-bench Verified — Original1,053Not specified · ExperimentalLongBench v21,014Not specified · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

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.

11 configurations · Publisher-run · Experimental conversion

1,053Best score · Not specified
Explore SWE-bench Verified — Original
LongBench v2

LongBench v2

Version LongBench-v2-503-20261106
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.

2 configurations · Publisher-run · Experimental conversion

1,014Best score · Not specified
Explore LongBench v2