Up to four models
Gemini 4 Hydrogen vs Claude Sonnet 5.5
On the index (GPT-4 = 100), Gemini 4 Hydrogen scores 191 and Claude Sonnet 5.5 187. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
191174–208
WeightsClosed
ReleasedNov 2026
Price in / out$1.5 / $7.5
Context1.05M
Core tests taken2 of 9
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
Gemini 4 Hydrogen and Claude Sonnet 5.5 are too close to call (4 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 1.3× less.
Test by testthird-party results
Every result as a table
| Test | Gemini 4 Hydrogen | Claude Sonnet 5.5 |
|---|---|---|
| Coding | ||
| Terminal-Bench 4.0 | 54.0% | 64.1% |
| Vibe Code Bench v1.1 | 87.8% | 92.4% |
| FrontierSWE | 53.1% | 61.9% |
| Agents | ||
| APEX-Agents | 78.0% | 75.5% |
| Professional work | ||
| HLAB-Vals-1.1 | 11.3% | 10.4% |
| Legal Research Bench | 53.8% | 48.1% |
| Tax Agent Bench | 52.3% | 42.0% |
Tests at least two of these models have taken. Bold rows are the core tests.