LuminaBench
Google / Published benchmarks

Gemma 4 31B

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

Arena Text — Style Controlled1,073Not specified · ExperimentalArena Vision — Style Controlled1,062Not specified · ExperimentalArena WebDev953Not specified · ExperimentalLiveBench 2.0841Max · ExperimentalGameBench 2958Reasoning enabled · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

Arena Text — Style Controlled

Arena Text — Style Controlled

Version Overall · Style controlled
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

1,073Best score · Not specified
Explore Arena Text — Style Controlled
Arena Vision — Style Controlled

Arena Vision — Style Controlled

Version Overall · Style controlled
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

1,062Best score · Not specified
Explore Arena Vision — Style Controlled
Arena WebDev

Arena WebDev

Version Overall
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

953Best score · Not specified
Explore Arena WebDev
LiveBench 2.0

LiveBench 2.0

Version 2.0 · 25 Oct 2026
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

841Best score · Max
Explore LiveBench 2.0
GameBench 2

GameBench 2

Version 2 · 8 games · B1 v19
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

958Best score · Reasoning enabled
Explore GameBench 2