LuminaBench
OpenAI / Published benchmarks

GPT-5.5

Benchmark results and API pricing.

Best recorded results

Benchmark scores

Best eligible score in each benchmark.

ARC-AGI-21,113xHigh · ExperimentalARC-AGI-3962High · ExperimentalGPQA Diamond1,077Low · ExperimentalMystery Game Puzzles1,147xHigh · ExperimentalLumina Reasoning Index1,116xHigh · 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.

4 configurations · Publisher-run · Experimental conversion

1,113Best score · xHigh
Explore ARC-AGI-2
ARC-AGI-3

ARC-AGI-3

Version 3
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

962Best score · High
Explore ARC-AGI-3
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.

2 configurations · Publisher-run · Experimental conversion

1,077Best score · Low
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.

4 configurations · Publisher-run · Experimental conversion

1,147Best score · xHigh
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.

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

1,116Provisional score · xHigh
Explore Lumina Reasoning Index