LIVE INTELLIGENCE · part of the Xentir AI Index

Claude Sonnet 4 vs DeepSeek-R1 (May 2025)

Claude Sonnet 4 · Anthropic, released 2025-05-22
DeepSeek-R1 (May 2025) OPEN WEIGHTS · DeepSeek, released 2025-05-28

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 4 of 9 tracked benchmarks for both models — Claude Sonnet 4 leads on 3, DeepSeek-R1 (May 2025) leads on 1.

Benchmark	Claude Sonnet 4	DeepSeek-R1 (May 2025)	Leads
Epoch Capabilities Index (ECI)	142.2	142.0	Claude Sonnet 4
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.783 (32k)	0.763	Claude Sonnet 4
MATH Level 5	0.844	0.966	DeepSeek-R1 (May 2025)
OTIS Mock AIME 2024-2025	0.711 (32k)	0.664	Claude Sonnet 4
FrontierMath	0.041	Not measured	Not measured on both
FrontierMath Tier 4	0.000	Not measured	Not measured on both
SimpleQA Verified	Not measured	0.274	Not measured on both
Chess Puzzles	Not measured	Not measured	Not measured on both

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

Claude Sonnet 4 → · DeepSeek-R1 (May 2025) → · the full AI Model Rankings table