Up to four models
DeepSeek-R1-0528 vs Gemma 4 26B A4B
On the index (GPT-4 = 100), DeepSeek-R1-0528 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.
135119–151
WeightsOpen
ReleasedApr 2026
Price in / out$0.076 / $0.26
Context262K
Core tests taken1 of 9
DeepSeek-R1-0528 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
Every result as a table
| Test | DeepSeek-R1-0528 | Gemma 4 26B A4B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 76.3% | 73.2% |
| Maths | ||
| AIME-style maths (OTIS mock) | 66.4% | 82.2% |
| Coding | ||
| WeirdML | 41.6% | 35.2% |
Task length · METR
32 sec
Tests at least two of these models have taken. Bold rows are the core tests.