The Model Index
Up to four models

GPT-6 Sol vs Hy4 preview

On the index (GPT-4 = 100), GPT-6 Sol scores 178 and Hy4 preview 173. 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 Sol
Presets
GPT-6 Sol
178162–194
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9
Hy4 preview
173154–192
WeightsOpen
ReleasedAug 2026
Price in / out$0.83 / $2.5
Context1.05M
Core tests taken2 of 9

GPT-6 Sol and Hy4 preview are too close to call (5 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, at 3.2× the price.

Test by testthird-party results

GPT-6 SolHy4 preview
0%25%50%75%100%MATHSProofBench v1.1ProofBench v1.1CODINGTerminal-Bench 4.0Terminal-Bench 4.0Code MigrationCode MigrationCyberBench v1.1CyberBench v1.1IOIIOIProgramBenchProgramBenchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSBioMysteryBenchBioMysteryBenchSRE BenchSRE BenchPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent Bench
Every result as a table
TestGPT-6 SolHy4 preview
Maths
ProofBench v1.183.0%75.0%
Coding
Terminal-Bench 4.044.4%39.4%
Code Migration57.2%47.4%
CyberBench v1.178.0%65.4%
IOI82.6%59.3%
ProgramBench2.0%0.0%
Vibe Code Bench v1.187.8%81.0%
Agents
BioMysteryBench74.8%69.3%
SRE Bench30.5%2.3%
Professional work
Finance Agent (v2)49.0%55.1%
EMB71.5%58.1%
Legal Research Bench28.8%45.2%
MedCode47.1%43.3%
MedScribe82.0%83.6%
Public Benefits Bench v1.156.6%68.6%
Tax Agent Bench15.0%34.4%

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

This page as a chartDownload PNG