The Model Index
Up to four models

DeepSeek-R1-0528 vs Claude 3.7 Sonnet

On the index (GPT-4 = 100), DeepSeek-R1-0528 scores 135 and Claude 3.7 Sonnet 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 DeepSeek-R1-0528
Presets
DeepSeek-R1-0528
135120–151
WeightsOpen
ReleasedMay 2025
Price in / out–
Context–
Core tests taken2 of 9
Claude 3.7 Sonnet
135119–151
WeightsClosed
ReleasedFeb 2025
Price in / out–
Context–
Core tests taken4 of 9

DeepSeek-R1-0528 and Claude 3.7 Sonnet are too close to call (0 points apart, within the uncertainty), ahead on 0 of 2 shared core tests.

Test by testthird-party results

DeepSeek-R1-0528Claude 3.7 Sonnet
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchSimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)CODINGAider PolyglotAider PolyglotAGENTSDeepResearch BenchDeepResearch Bench
Every result as a table
TestDeepSeek-R1-0528Claude 3.7 Sonnet
Reasoning & knowledge
GPQA Diamond (Epoch AI)76.3%79.7%
Fiction.LiveBench75.0%83.3%
SimpleBench40.8%46.4%
Maths
AIME-style maths (OTIS mock)66.4%57.8%
MATH (level 5)96.6%91.2%
Coding
Aider Polyglot71.4%64.9%
Agents
DeepResearch Bench35.1%43.6%
Task length · METR32 sec36 sec

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

This page as a chartDownload PNG