The Model Index
Up to four models

GPT-6 Luna vs GPT-5.2

On the index (GPT-4 = 100), GPT-6 Luna scores 162 and GPT-5.2 162. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-6 Luna
Presets
GPT-6 Luna
162146–178
WeightsClosed
ReleasedSep 2026
Price in / out$0.10 / $0.50
Context1.05M
Core tests taken6 of 9
GPT-5.2
162146–178
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9

GPT-6 Luna and GPT-5.2 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 3 shared core tests, and costs 24× less.

Test by testthird-party results

GPT-6 LunaGPT-5.2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGVibe Code Bench v1.1Vibe Code Bench v1.1MirrorCodeMirrorCodeAGENTSDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKMedCodeMedCodeMedScribeMedScribeNOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
TestGPT-6 LunaGPT-5.2
Reasoning & knowledge
GPQA Diamond (Epoch AI)90.5%91.4%
SimpleQA Verified41.4%37.1%
Maths
FrontierMath (tiers 1-3)79.0%67.4%
AIME-style maths (OTIS mock)98.9%96.1%
Chess puzzles36.0%48.0%
FrontierMath (tier 4)56.1%31.7%
Coding
Vibe Code Bench v1.181.7%53.5%
MirrorCode26.7%32.2%
Agents
DTBench90.1%90.9%
Furniture assembly44.2%38.3%
LMCA44.5%43.9%
Mystery game puzzles7.0%23.0%
Professional work
MedCode44.7%49.8%
MedScribe83.7%84.4%
Novel problems
ARC-AGI-259.3%72.9%
ARC-AGI-186.7%94.5%
Task length · METR45 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG