The Model Index
Up to four models

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

On the index (GPT-4 = 100), DeepSeek-R1-0528 scores 135 and Gemini 2.5 Flash (May 2025) 133. 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 DeepSeek-R1-0528
Presets
DeepSeek-R1-0528
135120–151
WeightsOpen
ReleasedMay 2025
Price in / out–
Context–
Core tests taken2 of 9
Gemini 2.5 Flash (May 2025)
133117–149
WeightsClosed
ReleasedMay 2025
Price in / out–
Context–
Core tests taken1 of 9

DeepSeek-R1-0528 and Gemini 2.5 Flash (May 2025) are too close to call (2 points apart, within the uncertainty).

Test by testthird-party results

DeepSeek-R1-0528Gemini 2.5 Flash (May 2025)
0%25%50%75%100%REASONING & KNOWLEDGEFiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGAider PolyglotAider PolyglotWeirdMLWeirdML
Every result as a table
TestDeepSeek-R1-0528Gemini 2.5 Flash (May 2025)
Reasoning & knowledge
Fiction.LiveBench75.0%77.8%
Maths
AIME-style maths (OTIS mock)66.4%70.8%
Coding
Aider Polyglot71.4%55.1%
WeirdML41.6%40.9%
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