LuminaBench
google / Published benchmarks

Gemini 3.1 Pro Preview (02/26)

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

BioMysteryBench913High · ExperimentalIOI985High · ExperimentalLegal Research Bench944High · ExperimentalLegalBench1,071High · ExperimentalMedCode1,146High · ExperimentalMedScribe982High · ExperimentalMysteryMechanism937High · ExperimentalProgramBench969High · ExperimentalProofBench v1.1930High · ExperimentalPublic Benefits Bench v1.1923High · ExperimentalSRE Bench938High · ExperimentalTax Agent Bench908High · ExperimentalTerminal-Bench-Science942High · 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

913Best score · High
Explore BioMysteryBench
IOI

IOI

Version 2-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

985Best score · High
Explore IOI
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

944Best score · High
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

1,071Best score · High
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

1,146Best score · High
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

982Best score · High
Explore MedScribe
MysteryMechanism

MysteryMechanism

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

937Best score · High
Explore MysteryMechanism
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 · High
Explore ProgramBench
ProofBench v1.1

ProofBench v1.1

Version 1.1-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

930Best score · High
Explore ProofBench v1.1
Public Benefits Bench v1.1

Public Benefits Bench v1.1

Version 1.1-updated-2026-10-12
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

923Best score · High
Explore Public Benefits Bench v1.1
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

938Best score · High
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

908Best score · High
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

942Best score · High
Explore Terminal-Bench-Science