LuminaBench
thinkingmachines / Published benchmarks

Models

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

BioMysteryBench1,0080.99 · ExperimentalCyberBench v1.11,0450.99 · ExperimentalEMB v1.11,0180.99 · ExperimentalFinance Agent v2.11,0900.99 · ExperimentalLegal Research Bench1,0720.99 · ExperimentalProgramBench9830.99 · ExperimentalSRE Bench9470.99 · ExperimentalTax Agent Bench1,0840.99 · ExperimentalTerminal-Bench-Science9480.99 · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

BioMysteryBench

BioMysteryBench

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

1,008Best score · 0.99
Explore BioMysteryBench
CyberBench v1.1

CyberBench v1.1

Version 1.1-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

1,045Best score · 0.99
Explore CyberBench v1.1
EMB v1.1

EMB v1.1

Version 1.1-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

1,018Best score · 0.99
Explore EMB v1.1
Finance Agent v2.1

Finance Agent v2.1

Version 2.1-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

1,090Best score · 0.99
Explore Finance Agent v2.1
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

1,072Best score · 0.99
Explore Legal Research Bench
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

983Best score · 0.99
Explore ProgramBench
SRE Bench

SRE 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

947Best score · 0.99
Explore SRE Bench
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

1,084Best score · 0.99
Explore Tax Agent Bench
Terminal-Bench-Science

Terminal-Bench-Science

Version 0.1-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

948Best score · 0.99
Explore Terminal-Bench-Science