The Model Index
Up to four models

GPT-6.2 vs GPT-6

On the index (GPT-4 = 100), GPT-6.2 scores 202 and GPT-6 193. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

GPT-6.2GPT-6
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
GPT-6
193178–209
WeightsClosed
ReleasedOct 2026
Price in / out–
Context–
Core tests taken7 of 9

GPT-6.2 and GPT-6 are too close to call (9 points apart, within the uncertainty), ahead on 2 of 3 shared core tests.

Test by testthird-party results

GPT-6.2GPT-6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)EBR-benchEBR-benchSimpleQA 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-6.2GPT-6
Reasoning & knowledge
GPQA Diamond (Epoch AI)96.8%95.8%
EBR-bench92.4%76.2%
SimpleQA Verified78.5%75.6%
Maths
FrontierMath (tiers 1-3)92.6%93.7%
AIME-style maths (OTIS mock)100.0%100.0%
Chess puzzles78.0%74.0%
FrontierMath (tier 4)100.0%97.6%
Coding
Terminal-Bench 4.063.1%59.6%
Vibe Code Bench v1.189.9%89.6%
MirrorCode67.8%60.0%
Agents
BioMysteryBench80.7%79.3%
Terminal-Bench-Science71.4%62.9%
Furniture assembly89.2%80.0%
Mystery game puzzles95.0%84.0%
Professional work
HLAB-Vals-1.116.3%7.1%
Legal Research Bench42.8%39.4%
Tax Agent Bench21.8%20.7%
Novel problems
MysteryMechanism53.1%53.1%

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

This page as a chartDownload PNG