LuminaBench
anthropic / Published benchmarks

Claude Opus 4.7

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

Legal Research Bench1,031Max · ExperimentalLegalBench1,054Max · ExperimentalMedCode1,111Max · ExperimentalMedScribe1,029Max · ExperimentalProgramBench969Max · ExperimentalTax Agent Bench994Max · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

Legal Research Bench

Legal Research Bench

Version 1-updated-2026-11-05
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

1,031Best score · Max
Explore Legal Research Bench
LegalBench

LegalBench

Version 1-updated-2026-10-13
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

1,054Best score · Max
Explore LegalBench
MedCode

MedCode

Version 1-updated-2026-10-29
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

1,111Best score · Max
Explore MedCode
MedScribe

MedScribe

Version 1-updated-2026-10-29
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

1,029Best score · Max
Explore MedScribe
ProgramBench

ProgramBench

Version 1-updated-2026-11-05
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

969Best score · Max
Explore ProgramBench
Tax Agent Bench

Tax Agent Bench

Version 1-updated-2026-11-05
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

994Best score · Max
Explore Tax Agent Bench