LuminaBench
Google DeepMind / Published benchmarks

gemini-3.1-pro-preview

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

FrontierMath Tier 4 v2971Not specified · ExperimentalMirrorCode909High · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

FrontierMath Tier 4 v2

FrontierMath Tier 4 v2

Version FrontierMath-Tier-4-v2-Private
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

971Best score · Not specified
Explore FrontierMath Tier 4 v2
MirrorCode

MirrorCode

Version ML-private-2-languages-30-tasks-v1
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

909Best score · High
Explore MirrorCode