Compare / Mistral Small 3 vs o3

Mistral Small 3 vs o3

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.

Mistral Small 3
Mistral · profile
o3
OpenAI · profile
Results compared
15
Shared sources
3

Mistral Small 3 or o3? The short answer

  • Mistral Small 3 is cheaper: $0.058 against $3.50 per million tokens, 61 times less.
  • o3 scores higher on the Artificial Analysis Intelligence Index: 20.2 against 6.7.
  • On our business benchmarks, Mistral Small 3 ranks higher for sticking to the facts.
  • On our business benchmarks, o3 ranks higher for reasoning and knowledge and writing.

At a glance

Mistral Small 3o3
Price per million tokens$0.050 in · $0.080 out$2.00 in · $8.00 out
Blended (3 in : 1 out)$0.058$3.50
Cheapest host, blended––
Intelligence Index6.720.2
Spring Prompt overall––
Output speed, tokens a second–126
Context window32,768 tokens200,000 tokens
WeightsOpenClosed
Developer based inFrancethe 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 caseMistral Small 3o3
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls not measured 13 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 190 of 195 95 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 155 of 187 49 of 187
Sticking to the factsSummarising without inventing things, and factual answers 11 of 153 91 of 153

Every shared result

BenchmarkMetricMistral Small 3o3
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,2591,426
Arena (formerly LMArena)reportedCreative writingArena rating 1,2271,383
Arena (formerly LMArena)reportedExpert promptsArena rating 1,2591,449
Arena (formerly LMArena)reportedInstruction followingArena rating 1,2551,403
Arena (formerly LMArena)reportedOverallArena rating 1,2741,432
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2481,396
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 6.7020.2
Artificial AnalysisreportedGPQA Diamond% of questions 46.2%82.7%
Artificial AnalysisreportedHumanity's Last Exam% of questions 3.8%20.1%
Artificial AnalysisreportedIFBench% of instructions 26.4%71.4%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 0.0%74.7%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 19.6%80.7%
UGI LeaderboardreportedRequested-length error% off the requested word count 8.0%18.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.350.30
UGI LeaderboardreportedWriting scorescore out of 100 33.966.8

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 Mistral Small 3 better than o3?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Mistral Small 3 ranks higher for sticking to the facts; o3 ranks higher for reasoning and knowledge and writing.

Which is cheaper, Mistral Small 3 or o3?

Mistral Small 3 costs $0.058 per million tokens (three input to one output), against $3.50 for o3.

Run Mistral Small 3 and o3 on your own prompt

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