The Model Index
Up to four models

Claude Fable 5.2 vs Gemini 4 Hydrogen

On the index (GPT-4 = 100), Claude Fable 5.2 scores 202 and Gemini 4 Hydrogen 191. 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 5.2
Presets
Claude Fable 5.2
202185–218
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1M
Core tests taken4 of 9
Gemini 4 Hydrogen
191174–208
WeightsClosed
ReleasedNov 2026
Price in / out$1.5 / $7.5
Context1.05M
Core tests taken2 of 9

Claude Fable 5.2 leads Gemini 4 Hydrogen by 11 points, ahead on 2 of 2 shared core tests, at 5.3× the price.

Test by testthird-party results

Claude Fable 5.2Gemini 4 Hydrogen
0%25%50%75%100%CODINGTerminal-Bench 4.0Terminal-Bench 4.0Vibe Code Bench v1.1Vibe Code Bench v1.1FrontierSWEFrontierSWEAGENTSAPEX-AgentsAPEX-AgentsPROFESSIONAL WORKHLAB-Vals-1.1HLAB-Vals-1.1Legal Research BenchLegal Research BenchTax Agent BenchTax Agent Bench
Every result as a table
TestClaude Fable 5.2Gemini 4 Hydrogen
Coding
Terminal-Bench 4.065.1%54.0%
Vibe Code Bench v1.193.8%87.8%
FrontierSWE69.9%53.1%
Agents
APEX-Agents80.1%78.0%
Professional work
HLAB-Vals-1.15.0%11.3%
Legal Research Bench46.2%53.8%
Tax Agent Bench32.1%52.3%

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

This page as a chartDownload PNG