Skip to content

DeepSeek-R1 (May 2025)

ModelOpen sourceActive
by DeepSeek · family “deepseek-r1-may”
Epoch Capabilities Index
141.3 #105 of 268
90% CI 138.8 – 143.1
Released
28 May 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (12)

BenchmarkDomainScorevs best recordedSettingRunSource
DeepResearch Benchagents35.1%
63%
——External ↗
ARC-AGI-2reasoning1.1%
1%
——External ↗
METR Time Horizonsagents53.8%
63%
——External ↗
Fiction.LiveBenchlong-context75.0%
77%
——External ↗
Lech Mazur Writingother81.9%
95%
——External ↗
WeirdMLcoding41.6% ±0.0
44%
——External ↗
Aider polyglotcoding71.4%
81%
——External ↗
OTIS Mock AIME 2024-2025math66.4% ±4.9
66%
—29 May 2025Eval log ↗
SimpleBenchreasoning40.8%
50%
——External ↗
GPQA diamondscience76.3% ±2.4
80%
—29 May 2025Eval log ↗
MATH level 5math96.6% ±0.4
98%
—29 May 2025Epoch ↗
ARC-AGIreasoning21.2%
22%
——External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 10h ago. Steps show when the price changed.

Events

No events recorded yet.