The Model Index
Up to four models

Claude Fable 5.1 vs Hy4 preview

On the index (GPT-4 = 100), Claude Fable 5.1 scores 189 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 Claude Fable 5.1
Presets
Claude Fable 5.1
189173–205
WeightsClosed
ReleasedSep 2026
Price in / out$10 / $50
Context1M
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

Claude Fable 5.1 leads Hy4 preview by 16 points, ahead on 2 of 2 shared core tests, at 16× the price.

Test by testthird-party results

Claude Fable 5.1Hy4 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 v1.1AGENTSSRE BenchSRE BenchPROFESSIONAL WORKFinance Agent (v2)Finance Agent (v2)EMBEMBLegalBenchLegalBenchLegal Research BenchLegal Research BenchMedCodeMedCodeMedScribeMedScribePublic Benefits Bench v1.1Public Benefits Bench v1.1Tax Agent BenchTax Agent Bench
Every result as a table
TestClaude Fable 5.1Hy4 preview
Maths
ProofBench v1.1100.0%75.0%
Coding
Terminal-Bench 4.058.1%39.4%
Code Migration54.6%47.4%
CyberBench v1.170.4%65.4%
IOI90.8%59.3%
ProgramBench7.0%0.0%
Vibe Code Bench v1.190.3%81.0%
Agents
SRE Bench22.9%2.3%
Professional work
Finance Agent (v2)58.9%55.1%
EMB76.7%58.1%
LegalBench88.5%83.8%
Legal Research Bench55.3%45.2%
MedCode53.5%43.3%
MedScribe91.3%83.6%
Public Benefits Bench v1.174.9%68.6%
Tax Agent Bench50.7%34.4%

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

This page as a chartDownload PNG