LuminaBench
DeepSeek / Published benchmarks

DeepSeek V4 Flash

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

ALE-Bench960High · ExperimentalGameBench 2986High (historical request variant 1) · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

ALE-Bench

ALE-Bench

Version 40 problems
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

960Best score · High
Explore ALE-Bench
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.

4 configurations · Publisher-run · Experimental conversion

986Best score · High (historical request variant 1)
Explore GameBench 2