The Model Index
Up to four models

Gemini 2.5 Pro (May 2025) vs DeepSeek-R1-0528

On the index (GPT-4 = 100), Gemini 2.5 Pro (May 2025) 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 Gemini 2.5 Pro (May 2025)
Presets
Gemini 2.5 Pro (May 2025)
137121–153
WeightsClosed
ReleasedMay 2025
Price in / out–
Context–
Core tests taken2 of 9
DeepSeek-R1-0528
135120–151
WeightsOpen
ReleasedMay 2025
Price in / out–
Context–
Core tests taken2 of 9

Gemini 2.5 Pro (May 2025) 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

Gemini 2.5 Pro (May 2025)DeepSeek-R1-0528
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchMATHSMATH (level 5)MATH (level 5)CODINGAider PolyglotAider Polyglot
Every result as a table
TestGemini 2.5 Pro (May 2025)DeepSeek-R1-0528
Reasoning & knowledge
GPQA Diamond (Epoch AI)66.7%76.3%
Fiction.LiveBench66.7%75.0%
Maths
MATH (level 5)95.9%96.6%
Coding
Aider Polyglot76.9%71.4%
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