Compare / Mercury 2 vs Mistral Medium 3.1
Mercury 2 vs Mistral Medium 3.1
Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.
Mercury 2 or Mistral Medium 3.1? The short answer
- Mercury 2 is cheaper: $0.38 against $0.80 per million tokens, 2.1 times less.
- Mercury 2 scores higher on the Artificial Analysis Intelligence Index: 13.8 against 9.2.
- On our business benchmarks, Mercury 2 ranks higher for agents and tool use and reasoning and knowledge.
- On our business benchmarks, Mistral Medium 3.1 ranks higher for writing and sticking to the facts.
At a glance
| Mercury 2 | Mistral Medium 3.1 | |
|---|---|---|
| Price per million tokens | $0.25 in · $0.75 out | $0.40 in · $2.00 out |
| Blended (3 in : 1 out) | $0.38 | $0.80 |
| Cheapest host, blended | – | $0.80 (Mistral) |
| Intelligence Index | 13.8 | 9.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 128,000 tokens | 131,072 tokens |
| Weights | Closed | Closed |
| Developer based in | the US | France |
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 case | Mercury 2 | Mistral Medium 3.1 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 107 of 161 | 119 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 109 of 195 | 157 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 146 of 187 | 110 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 136 of 153 | 130 of 153 |
Every shared result
| Benchmark | Metric | Mercury 2 | Mistral Medium 3.1 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,368 | 1,429 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,340 | 1,407 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,292 | 1,378 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,348 | 1,410 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,327 | 1,395 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,343 | 1,408 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,307 | 1,386 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 31.1 | 20.5 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 13.8 | 9.20 |
| Artificial Analysisreported | GPQA Diamond% of questions | 77.0% | 58.8% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 17.1% | 4.7% |
| Artificial Analysisreported | IFBench% of instructions | 69.8% | 39.8% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 43.7% | 42.7% |
| Artificial Analysisreported | SciCode% of problems | 37.7% | 32.4% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 27.3% | 13.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 26.5% | 10.6% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 9.5% | 8.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 70.8% | 40.6% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 100.0% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.3% | 22.7% |
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 Mistral Medium 3.1?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Mercury 2 ranks higher for agents and tool use and reasoning and knowledge; Mistral Medium 3.1 ranks higher for writing and sticking to the facts.
Which is cheaper, Mercury 2 or Mistral Medium 3.1?
Mercury 2 costs $0.38 per million tokens (three input to one output), against $0.80 for Mistral Medium 3.1.
Run Mercury 2 and Mistral Medium 3.1 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.