The Model Index
Up to four models

Gemma 4 vs DeepSeek-R1-0528

On the index (GPT-4 = 100), Gemma 4 scores 137 and DeepSeek-R1-0528 135. 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 Gemma 4
Presets
Gemma 4
137121–154
WeightsOpen
ReleasedApr 2026
Price in / out–
Context–
Core tests taken1 of 9
DeepSeek-R1-0528
135120–151
WeightsOpen
ReleasedMay 2025
Price in / out–
Context–
Core tests taken2 of 9

Gemma 4 and DeepSeek-R1-0528 are too close to call (2 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Gemma 4DeepSeek-R1-0528
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGWeirdMLWeirdML
Every result as a table
TestGemma 4DeepSeek-R1-0528
Reasoning & knowledge
GPQA Diamond (Epoch AI)75.8%76.3%
Maths
AIME-style maths (OTIS mock)73.3%66.4%
Coding
WeirdML52.3%41.6%
Task length · METR32 sec

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

This page as a chartDownload PNG