Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d262Policy30d65, 14 pendingSources1,013

DeepSeek-R1 0528

DeepSeekReleased May 28, 2025Current

Score basis

DeepSeek-R1 0528 is behind the leaders in long context, reasoning, coding, and agentic tasks. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, instruction following, or factuality.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited4 capabilities
  1. Long Context−36.3%2 of 3
  2. Reasoning−40.7%5 of 6
  3. Coding−41.4%4 of 10
  4. Agentic−46.2%2 of 7
Not rated6 capabilities

Too few results yet to rate Safety, Math, Multimodal, Multilingual, Instruction Following or Factuality.

Price

$1.35input$3.00outputper million tokens

From Artificial Analysis · 4 providers tracked · All prices

Costs more than 69% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

75results on57benchmarks

  • 20 independently verified
  • 15 aggregator
  • 24 vendor-reported
  • 16 cross-referenced

From 22 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

DeepSeek-R1 0528 benchmark results

75 results on 57 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

LimitedFull long context ranking

36.3% behind the leader2 of 3 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

40.7% behind the leader5 of 6 ranked benchmarks measured

Show 4 more reasoning resultsHide 4 reasoning results

Coding

LimitedFull coding ranking

41.4% behind the leader4 of 10 ranked benchmarks measured

Show 2 more coding resultsHide 2 coding results

Agentic

LimitedFull agentic ranking

46.2% behind the leader2 of 7 ranked benchmarks measured

Instruction Following

Not enough dataFull instruction following ranking

0 of 3 ranked benchmarks measured

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 45 more resultsHide 45 results

DeepSeek-R1 0528: common questions

Who makes DeepSeek-R1 0528?

DeepSeek-R1 0528 is made by DeepSeek.

When was DeepSeek-R1 0528 released?

DeepSeek-R1 0528 was released on May 28, 2025, according to Artificial Analysis.

What is DeepSeek-R1 0528 good at?

DeepSeek-R1 0528 is behind the leaders in long context, reasoning, coding, and agentic tasks. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, instruction following, or factuality.

How much does DeepSeek-R1 0528 cost?

DeepSeek-R1 0528 costs $1.35 per million input tokens and $3.00 per million output tokens, according to Artificial Analysis. We track its price at 4 providers. At a mix of three input tokens to one output token, it costs more than 69% of the 331 priced models we track.

How many benchmarks has DeepSeek-R1 0528 been tested on?

We track 75 results for DeepSeek-R1 0528 on 57 benchmarks from 22 sources, 20 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does DeepSeek-R1 0528 support?

OpenRouter lists tool calling, structured outputs, and reasoning for DeepSeek-R1 0528.

About this record

Where DeepSeek-R1 0528's numbers come from, and every name it appears under.

Tracked since
May 2, 2026
Newest source mention
Sep 10, 2026

Where the results come from

Verification: 75 scores · 20 independently verified · 15 aggregator-attributed · 16 vendor cross-reference · 24 vendor-reported. How these tiers are assigned

From 22 sources on 10 sites. Hugging Face supplies 26 of them; the 20 independently verified results come from 7 sites. Bars are coloured by trust tier.

  • huggingface.co26
  • artificialanalysis.ai15
  • api.llm-stats.com14
  • matharena.ai6
  • storage.googleapis.com5
  • livecodebench.github.io4
  • arcprize.org2
  • aider.chat1
  • epoch.ai1
  • simple-bench.com1

Also known as

deepseek r1 0528 (may '25)deepseek r1 (0528)deepseek r1 (05/28)deepseek r1 05/28