Compare / R1 vs Gemini 2.5 Flash

R1 vs Gemini 2.5 Flash

Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.

R1
DeepSeek · profile
Gemini 2.5 Flash
Google · profile
Results compared
15
Shared sources
3

R1 or Gemini 2.5 Flash? The short answer

  • Gemini 2.5 Flash is cheaper: $0.85 against $1.15 per million tokens, 26% less.
  • Gemini 2.5 Flash 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, Gemini 2.5 Flash ranks higher for agents and tool use, reasoning and knowledge and sticking to the facts.

At a glance

R1Gemini 2.5 Flash
Price per million tokens$0.70 in · $2.50 out$0.30 in · $2.50 out
Blended (3 in : 1 out)$1.15$0.85
Cheapest host, blended–$0.42 (Google AI Studio)
Intelligence Index11.413.1
Spring Prompt overall––
Output speed, tokens a second––
Context window64,000 tokens1,048,576 tokens
WeightsOpenClosed
Developer based inChinathe US

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 caseR1Gemini 2.5 Flash
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 123 of 161 74 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 133 of 195 115 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 89 of 187 93 of 187
Sticking to the factsSummarising without inventing things, and factual answers 110 of 153 66 of 153

Every shared result

BenchmarkMetricR1Gemini 2.5 Flash
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3881,399
Arena (formerly LMArena)reportedCreative writingArena rating 1,3741,394
Arena (formerly LMArena)reportedExpert promptsArena rating 1,4021,424
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3971,400
Arena (formerly LMArena)reportedOverallArena rating 1,3981,409
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3821,402
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 11.413.1
Artificial AnalysisreportedGPQA Diamond% of questions 70.8%79.0%
Artificial AnalysisreportedHumanity's Last Exam% of questions 8.5%12.1%
Artificial AnalysisreportedIFBench% of instructions 39.0%50.3%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 57.7%65.3%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 6.1%13.6%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 11.4%31.6%
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 97.0%99.0%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 11.3%7.8%

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 Gemini 2.5 Flash?

It depends on the task. Among models available today, on our benchmarks and licensed sources, R1 ranks higher for writing; Gemini 2.5 Flash ranks higher for agents and tool use, reasoning and knowledge and sticking to the facts.

Which is cheaper, R1 or Gemini 2.5 Flash?

Gemini 2.5 Flash costs $0.85 per million tokens (three input to one output), against $1.15 for R1.

Run R1 and Gemini 2.5 Flash on your own prompt

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