Kimi K2.7 Code
VS
Mistral Medium 3.1
Kimi K2.7 Code 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.
Kimi K2.7 Code wins 20 of 22 task areas we tested; Mistral Medium 3.1 takes 2. Mistral Medium 3.1 costs 1.8× less per token ($2.4 vs $4.24 per 1M).
Mistral Medium 3.1 costs 1.8× less per token ($2.4 vs $4.24 per 1M).
Task by task
| Task area | Kimi K2.7 Code | Mistral Medium 3.1 | Winner |
|---|---|---|---|
| Customer Support |
#10
/ 113
Strong
|
#110
/ 113
Needs editing
|
Kimi K2.7 Code |
| Presentations & Decks |
#5
/ 110
Excellent
|
#105
/ 110
Usable
|
Kimi K2.7 Code |
| RAG, Safety & Grounding |
#21
/ 113
Excellent
|
#111
/ 113
Strong
|
Kimi K2.7 Code |
| Executive Assistant |
#6
/ 112
Strong
|
#94
/ 112
Usable
|
Kimi K2.7 Code |
| Research & Competitive Analysis |
#20
/ 110
Excellent
|
#105
/ 110
Weak
|
Kimi K2.7 Code |
| AI Strategy |
#44
/ 126
Strong
|
#120
/ 126
Usable
|
Kimi K2.7 Code |
| Coding |
#41
/ 115
Strong
|
#108
/ 115
Needs editing
|
Kimi K2.7 Code |
| Content & Brand |
#48
/ 124
Strong
|
#110
/ 124
Needs editing
|
Kimi K2.7 Code |
| Knowledge & Docs |
#16
/ 110
Excellent
|
#77
/ 110
Usable
|
Kimi K2.7 Code |
| Chef / Home Cooking |
#58
/ 126
Usable
|
#116
/ 126
Needs editing
|
Kimi K2.7 Code |
| Creative & Comedy | #44 / 110 | #100 / 110 | Kimi K2.7 Code |
| Data & Analytics |
#31
/ 110
Excellent
|
#87
/ 110
Excellent
|
Kimi K2.7 Code |
| Legal & HR |
#14
/ 110
Excellent
|
#70
/ 110
Strong
|
Kimi K2.7 Code |
| Investor & Pitch |
#15
/ 66
Strong
|
#65
/ 66
Needs editing
|
Kimi K2.7 Code |
| Landing Pages |
#17
/ 72
Strong
|
#63
/ 72
Usable
|
Kimi K2.7 Code |
| Structured Output |
#46
/ 113
Excellent
|
#91
/ 113
Strong
|
Kimi K2.7 Code |
| Sales |
#48
/ 110
Usable
|
#92
/ 110
Usable
|
Kimi K2.7 Code |
| Product & Project Management |
#10
/ 110
Excellent
|
#50
/ 110
Strong
|
Kimi K2.7 Code |
| Frontend & Landing Pages |
#54
/ 109
Needs editing
|
#35
/ 109
Needs editing
|
Mistral Medium 3.1 |
| Summarization & Meeting Notes |
#47
/ 110
Excellent
|
#39
/ 110
Excellent
|
Mistral Medium 3.1 |
| Training & Education |
#39
/ 110
Excellent
|
#47
/ 110
Excellent
|
Kimi K2.7 Code |
| Translation & Localization |
#48
/ 110
Excellent
|
#53
/ 110
Excellent
|
Kimi K2.7 Code |
Rank = position among every model config we tested in that task area (lower is better). Sorted by biggest gap first.
Frequently asked
Is Kimi K2.7 Code better than Mistral Medium 3.1?
Across 22 task areas we benchmarked, Kimi K2.7 Code ranks higher in 20 and Mistral Medium 3.1 in 2.
Which is cheaper, Kimi K2.7 Code or Mistral Medium 3.1?
Mistral Medium 3.1 costs 1.8× less per token ($2.4 vs $4.24 per 1M).
What is Kimi K2.7 Code better at?
Kimi K2.7 Code out-ranks Mistral Medium 3.1 at Customer Support, Presentations & Decks, RAG, Safety & Grounding.
What is Mistral Medium 3.1 better at?
Mistral Medium 3.1 out-ranks Kimi K2.7 Code at Frontend & Landing Pages, Summarization & Meeting Notes.
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