DeepSeek-R1

Name: DeepSeek-R1
Rating: 80.4 (12000 reviews)
Author: DeepSeek

#55Large Language ModelsOpen Weights

DeepSeek

DeepSeek's reasoning-focused model trained with reinforcement learning, rivaling OpenAI o1 at a fraction of the cost.

Running this yourself: likely needs a high-memory cloud gpu.

Model updates refreshed6m agoMay 21, 2026news + changelog

View Updates Start Free Trial

80.4

Quality Score

1373

Arena ELO

671B

Parameters

128K

Context

Benchmarks and Competitive Signal

Structured

Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.

This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.

LiveBench Languagelanguage

Similar Models

Discussion (0)

Loading comments...

Official Benchmark Evidence

These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.

deepseek-r1 - Arena-Hard-Auto

Benchmarksarena-hard-autoMay 21, 2026

Arena-Hard-Auto official Gemini-2.5 judged score 58.0 with CI -2.2/2

View source

DeepSeek R1 Benchmark Update

Benchmarksartificial-analysisMay 18, 2026

Quality: 89/100 | Speed: 35/100 | Price: $0.55/M tokens | MMLU: 90.8%

View source

DeepSeek R1 Benchmark Update

Benchmarksartificial-analysisMay 17, 2026

Quality: 89/100 | Speed: 35/100 | Price: $0.55/M tokens | MMLU: 90.8%

View source