Compare / Mercury 2 vs o4 Mini

Mercury 2 vs o4 Mini

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.

Mercury 2
Inception · profile
o4 Mini
OpenAI · profile
Results compared
16
Shared sources
3

Mercury 2 or o4 Mini? The short answer

  • Mercury 2 is cheaper: $0.38 against $1.93 per million tokens, 5.1 times less.
  • o4 Mini scores higher on the Artificial Analysis Intelligence Index: 16.7 against 13.8.
  • On our business benchmarks, Mercury 2 ranks higher for sticking to the facts.
  • On our business benchmarks, o4 Mini ranks higher for agents and tool use, reasoning and knowledge and writing.

At a glance

Mercury 2o4 Mini
Price per million tokens$0.25 in · $0.75 out$1.10 in · $4.40 out
Blended (3 in : 1 out)$0.38$1.93
Cheapest host, blended––
Intelligence Index13.816.7
Spring Prompt overall––
Output speed, tokens a second––
Context window128,000 tokens200,000 tokens
WeightsClosedClosed
Developer based inthe USthe 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 caseMercury 2o4 Mini
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 107 of 161 46 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 109 of 195 101 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 146 of 187 98 of 187
Sticking to the factsSummarising without inventing things, and factual answers 136 of 153 141 of 153

Every shared result

BenchmarkMetricMercury 2o4 Mini
Arena (formerly LMArena)reportedOverallArena rating 1,3681,368
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3401,379
Arena (formerly LMArena)reportedCreative writingArena rating 1,2921,337
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3481,408
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3271,369
Arena (formerly LMArena)reportedOverallArena rating 1,3431,391
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3071,354
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 13.816.7
Artificial AnalysisreportedGPQA Diamond% of questions 77.0%78.4%
Artificial AnalysisreportedHumanity's Last Exam% of questions 17.1%16.5%
Artificial AnalysisreportedIFBench% of instructions 69.8%68.7%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 43.7%61.0%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 26.5%15.2%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 70.8%55.6%
Vectara Hallucination LeaderboardreportedAnswer rate% of documents 100.0%98.7%
Vectara Hallucination LeaderboardreportedHallucination rate% of summaries 12.3%18.6%

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 Mercury 2 better than o4 Mini?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Mercury 2 ranks higher for sticking to the facts; o4 Mini ranks higher for agents and tool use, reasoning and knowledge and writing.

Which is cheaper, Mercury 2 or o4 Mini?

Mercury 2 costs $0.38 per million tokens (three input to one output), against $1.93 for o4 Mini.

Run Mercury 2 and o4 Mini on your own prompt

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