Compare / R1 vs R1 0528

R1 vs R1 0528

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

R1
DeepSeek · profile
R1 0528
DeepSeek · profile
Results compared
16
Shared sources
3

R1 or R1 0528? The short answer

  • R1 0528 is cheaper: $0.92 against $1.15 per million tokens, 20% less.
  • R1 0528 scores higher on the Artificial Analysis Intelligence Index: 13.1 against 11.4.
  • On our business benchmarks, R1 ranks higher for writing.
  • On our business benchmarks, R1 0528 ranks higher for reasoning and knowledge.

At a glance

R1R1 0528
Price per million tokens$0.70 in · $2.50 out$0.50 in · $2.18 out
Blended (3 in : 1 out)$1.15$0.92
Cheapest host, blended–$0.91 (DeepInfra, FP4)
Intelligence Index11.413.1
Spring Prompt overall––
Output speed, tokens a second––
Context window64,000 tokens163,840 tokens
WeightsOpenOpen
Developer based inChinaChina

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseR1R1 0528
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 123 of 161 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 133 of 195 106 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 89 of 187 90 of 187
Sticking to the factsSummarising without inventing things, and factual answers 110 of 153 not measured

Every shared result

BenchmarkMetricR1R1 0528
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3881,407
Arena (formerly LMArena)reportedCreative writingArena rating 1,3741,389
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4021,418
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3971,391
Arena (formerly LMArena)reportedOverallArena rating 1,3981,422
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3821,388
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 11.413.1
Artificial AnalysisreportedGPQA Diamond% of questions 70.8%81.3%
Artificial AnalysisreportedHumanity's Last Exam% of questions 8.5%15.8%
Artificial AnalysisreportedIFBench% of instructions 39.0%39.6%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 57.7%55.7%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 6.1%15.9%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 11.4%36.5%
UGI LeaderboardreportedRequested-length error% off the requested word count 18.0%45.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.300.32
UGI LeaderboardreportedWriting scorescore out of 100 51.842.3

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is R1 better than R1 0528?

It depends on the task. Among models available today, on our benchmarks and licensed sources, R1 ranks higher for writing; R1 0528 ranks higher for reasoning and knowledge.

Which is cheaper, R1 or R1 0528?

R1 0528 costs $0.92 per million tokens (three input to one output), against $1.15 for R1.

Run R1 and R1 0528 on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.