MiniMax M2.7
VS
Mistral Medium 3.1
MiniMax M2.7 vs Mistral Medium 3.1: which wins at real work?
22 task areas · same graded test runs · rank comparison only, so 0–100 and Elo collections never mix raw scores.
Mistral Medium 3.1 wins 14 of 22 task areas we tested; MiniMax M2.7 takes 8. MiniMax M2.7 costs 2.7× less per token ($0.9 vs $2.4 per 1M).
MiniMax M2.7 costs 2.7× less per token ($0.9 vs $2.4 per 1M).
Task by task
| Task area | MiniMax M2.7 | Mistral Medium 3.1 | Winner |
|---|---|---|---|
| Summarization & Meeting Notes |
#104
/ 110
Strong
|
#39
/ 110
Excellent
|
Mistral Medium 3.1 |
| Training & Education |
#106
/ 110
Usable
|
#47
/ 110
Excellent
|
Mistral Medium 3.1 |
| Structured Output |
#33
/ 113
Excellent
|
#91
/ 113
Strong
|
MiniMax M2.7 |
| Frontend & Landing Pages |
#89
/ 109
Weak
|
#35
/ 109
Needs editing
|
Mistral Medium 3.1 |
| Knowledge & Docs |
#108
/ 110
Weak
|
#77
/ 110
Usable
|
Mistral Medium 3.1 |
| Translation & Localization |
#82
/ 110
Excellent
|
#53
/ 110
Excellent
|
Mistral Medium 3.1 |
| Presentations & Decks |
#83
/ 110
Strong
|
#105
/ 110
Usable
|
MiniMax M2.7 |
| RAG, Safety & Grounding |
#94
/ 113
Strong
|
#111
/ 113
Strong
|
MiniMax M2.7 |
| Sales |
#108
/ 110
Weak
|
#92
/ 110
Usable
|
Mistral Medium 3.1 |
| Content & Brand |
#96
/ 124
Usable
|
#110
/ 124
Needs editing
|
MiniMax M2.7 |
| Product & Project Management |
#64
/ 110
Strong
|
#50
/ 110
Strong
|
Mistral Medium 3.1 |
| Executive Assistant |
#107
/ 112
Usable
|
#94
/ 112
Usable
|
Mistral Medium 3.1 |
| Legal & HR |
#81
/ 110
Strong
|
#70
/ 110
Strong
|
Mistral Medium 3.1 |
| Research & Competitive Analysis |
#96
/ 110
Needs editing
|
#105
/ 110
Weak
|
MiniMax M2.7 |
| Chef / Home Cooking |
#124
/ 126
Weak
|
#116
/ 126
Needs editing
|
Mistral Medium 3.1 |
| Creative & Comedy | #108 / 110 | #100 / 110 | Mistral Medium 3.1 |
| Data & Analytics |
#92
/ 110
Excellent
|
#87
/ 110
Excellent
|
Mistral Medium 3.1 |
| Landing Pages |
#68
/ 72
Needs editing
|
#63
/ 72
Usable
|
Mistral Medium 3.1 |
| Coding |
#105
/ 115
Usable
|
#108
/ 115
Needs editing
|
MiniMax M2.7 |
| Customer Support |
#108
/ 113
Needs editing
|
#110
/ 113
Needs editing
|
MiniMax M2.7 |
| AI Strategy |
#119
/ 126
Usable
|
#120
/ 126
Usable
|
MiniMax M2.7 |
| Investor & Pitch |
#66
/ 66
Weak
|
#65
/ 66
Needs editing
|
Mistral Medium 3.1 |
Rank = position among every model config we tested in that task area (lower is better). Sorted by biggest gap first.
Frequently asked
Is MiniMax M2.7 better than Mistral Medium 3.1?
Across 22 task areas we benchmarked, Mistral Medium 3.1 ranks higher in 14 and MiniMax M2.7 in 8.
Which is cheaper, MiniMax M2.7 or Mistral Medium 3.1?
MiniMax M2.7 costs 2.7× less per token ($0.9 vs $2.4 per 1M).
What is MiniMax M2.7 better at?
MiniMax M2.7 out-ranks Mistral Medium 3.1 at Structured Output, Presentations & Decks, RAG, Safety & Grounding.
What is Mistral Medium 3.1 better at?
Mistral Medium 3.1 out-ranks MiniMax M2.7 at Summarization & Meeting Notes, Training & Education, Frontend & Landing Pages.
More comparisons
This page is Spring Prompt, running in public
We just did this for every model. Do it for your prompt.
The rankings above come from running real tasks through real models and scoring every output. Spring Prompt is that same engine — pointed at your prompt, your test cases, and your definition of good.
- Generate test cases from your prompt — no eval set required to start.
- Compare models side by side with quality, cost and latency in one matrix.
- Optimise the winner until the scores say it's ready to ship.
Prompt × model results
12 test cases · 3 evals