The Model Index
Up to four models

GPT-6.2 vs Claude Sonnet 5.5

On the index (GPT-4 = 100), GPT-6.2 scores 202 and Claude Sonnet 5.5 187. 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-6.2
Presets
GPT-6.2
202184–220
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1.05M
Core tests taken3 of 9
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9

GPT-6.2 leads Claude Sonnet 5.5 by 15 points, ahead on 2 of 3 shared core tests, at 4.0× the price.

Test by testthird-party results

GPT-6.2Claude Sonnet 5.5
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)CODINGTerminal-Bench 4.0Terminal-Bench 4.0Vibe Code Bench v1.1Vibe Code Bench v1.1MirrorCodeMirrorCodeAGENTSBioMysteryBenchBioMysteryBenchTerminal-Bench-ScienceTerminal-Bench-ScienceFurniture assemblyFurniture assemblyMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKHLAB-Vals-1.1HLAB-Vals-1.1Legal Research BenchLegal Research BenchTax Agent BenchTax Agent BenchNOVEL PROBLEMSMysteryMechanismMysteryMechanism
Every result as a table
TestGPT-6.2Claude Sonnet 5.5
Reasoning & knowledge
GPQA Diamond (Epoch AI)96.8%95.6%
SimpleQA Verified78.5%46.5%
Maths
FrontierMath (tiers 1-3)92.6%88.8%
AIME-style maths (OTIS mock)100.0%100.0%
Chess puzzles78.0%59.0%
FrontierMath (tier 4)100.0%80.5%
Coding
Terminal-Bench 4.063.1%64.1%
Vibe Code Bench v1.189.9%92.4%
MirrorCode67.8%97.8%
Agents
BioMysteryBench80.7%81.1%
Terminal-Bench-Science71.4%47.1%
Furniture assembly89.2%75.0%
Mystery game puzzles95.0%65.0%
Professional work
HLAB-Vals-1.116.3%10.4%
Legal Research Bench42.8%48.1%
Tax Agent Bench21.8%42.0%
Novel problems
MysteryMechanism53.1%49.1%

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

This page as a chartDownload PNG