The Model Index
Up to four models

GPT-6.2 vs Inkling 2 Small

On the index (GPT-4 = 100), GPT-6.2 scores 202 and Inkling 2 Small 166. 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
Inkling 2 Small
166149–183
WeightsOpen
ReleasedNov 2026
Price in / out$0.30 / $1.0
Context1.05M
Core tests taken2 of 9

GPT-6.2 leads Inkling 2 Small by 36 points, ahead on 1 of 1 shared core tests, at 34× the price.

Test by testthird-party results

GPT-6.2Inkling 2 Small
0%25%50%75%100%CODINGTerminal-Bench 4.0Terminal-Bench 4.0TMVibe Code Bench v1.1Vibe Code Bench v1.1TMAGENTSBioMysteryBenchBioMysteryBenchTMTerminal-Bench-ScienceTerminal-Bench-ScienceTMPROFESSIONAL WORKHLAB-Vals-1.1HLAB-Vals-1.1TMLegal Research BenchLegal Research BenchTMTax Agent BenchTax Agent BenchTMNOVEL PROBLEMSMysteryMechanismMysteryMechanismTM
Every result as a table
TestGPT-6.2Inkling 2 Small
Coding
Terminal-Bench 4.063.1%12.6%
Vibe Code Bench v1.189.9%81.5%
Agents
BioMysteryBench80.7%70.0%
Terminal-Bench-Science71.4%2.9%
Professional work
HLAB-Vals-1.116.3%21.7%
Legal Research Bench42.8%46.6%
Tax Agent Bench21.8%38.9%
Novel problems
MysteryMechanism53.1%25.2%

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

This page as a chartDownload PNG