LuminaBench
Anthropic / Published benchmarks

Claude Sonnet 4.6

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

ARC-AGI-21,057High · ExperimentalGPQA Diamond1,06632K · ExperimentalMystery Game Puzzles968Low · ExperimentalLumina Reasoning Index1,055High · 2/3 Provisional · Experimental

API pricing

USD / 1M tokens

Verified pricing is unavailable for this model.

ARC-AGI-2

ARC-AGI-2

Version 2
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

1,057Best score · High
Explore ARC-AGI-2
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.

4 configurations · Publisher-run · Experimental conversion

1,066Best score · 32K
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.

2 configurations · Publisher-run · Experimental conversion

968Best score · Low
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.

6 configurations · Derived from published benchmarks · Experimental · 2/3 Provisional

1,055Provisional score · High
Explore Lumina Reasoning Index