LuminaBench
DeepSeek / Published benchmarks

DeepSeek V4 Pro

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

HLE-Diamond893Not specified · ExperimentalGPQA Diamond1,078High · ExperimentalMystery Game Puzzles972None · ExperimentalLumina Reasoning Index1,070High · 1/3 Provisional · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

HLE-Diamond

HLE-Diamond

Version Diamond-1000
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

893Best score · Not specified
Explore HLE-Diamond
GPQA Diamond

GPQA Diamond

Version Diamond-198
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.

3 configurations · Publisher-run · Experimental conversion

1,078Best score · High
Explore GPQA Diamond
Mystery Game Puzzles

Mystery Game Puzzles

Version Puzzles-100
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

972Best score · None
Explore Mystery Game Puzzles

Lumina Reasoning Index

Version 3
By LuminaIndex designed by LuminaBench using attributed, publisher-run benchmarks. Lumina did not rerun those evaluations.

3 configurations · Derived from published benchmarks · Experimental · 1/3 Provisional

1,070Provisional score · High
Explore Lumina Reasoning Index