Up to four models
Claude 3.7 Sonnet vs Gemma 4 26B A4B
On the index (GPT-4 = 100), Claude 3.7 Sonnet scores 135 and Gemma 4 26B A4B 135. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude 3.7 Sonnet
135119–151
WeightsClosed
ReleasedFeb 2025
Price in / out–
Context–
Core tests taken4 of 9
135119–151
WeightsOpen
ReleasedApr 2026
Price in / out$0.076 / $0.26
Context262K
Core tests taken1 of 9
Claude 3.7 Sonnet and Gemma 4 26B A4B are too close to call (0 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.
Test by testthird-party results
Claude 3.7 Sonnet
Gemma 4 26B A4B
Every result as a table
| Test | Claude 3.7 Sonnet | Gemma 4 26B A4B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 79.7% | 73.2% |
| Maths | ||
| AIME-style maths (OTIS mock) | 57.8% | 82.2% |
Task length · METR36 sec
Tests at least two of these models have taken. Bold rows are the core tests.