Kimi K2.5 vs MiniMax M2.7
Kimi K2.5 leads MiniMax M2.7 on coding, 38.6 to 36.2 on the Vibe Coding Index, and MiniMax M2.7 costs 2.4x less per output token ($1.20 vs $2.85 per million). Updated October 22, 2026; 67 benchmarks have a result for both.
Kimi K2.5 or MiniMax M2.7: which to pick
Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 36.2 for MiniMax M2.7.
Pick MiniMax M2.7 for output tokens 2.4x cheaper ($1.20 vs $2.85 per million) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.
- Shared results
- 67
- Kimi K2.5 only
- 32
- MiniMax M2.7 only
- 7
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Kimi K2.5
Kimi K2.5 scores 38.6 against 36.2.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
Kimi K2.5
Kimi K2.5 leads, 23.5 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiniMax M2.7 has a AA Agentic Index result, 15.3.
Directional only
Reasoning
GPQA Diamond
MiniMax M2.7
MiniMax M2.7 leads, 86.6% against 84.1%.
Same board, both measured
Math
AIME
Kimi K2.5
Kimi K2.5 leads, 95.6% against 91.0%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K2.5
Kimi K2.5 leads, 85.9% against 80.4%.
Same board, both measured
Web design
Design Arena: websites
Kimi K2.5
Kimi K2.5 leads, 1248 against 1243.
Same board, both measured
Long documents
Listed context window
Kimi K2.5
Kimi K2.5 takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.7
Kimi K2.5 $0.0020, MiniMax M2.7 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Kimi K2.5
Kimi K2.5 $0.24, MiniMax M2.7 $0.64.
Published attempt cost and pass rate
At a glance
- Coding index
- Kimi K2.5 38.6 from 3 benchmarks, MiniMax M2.7 36.2 from 3 benchmarks.
- Widest category
- General, 8.1 points apart on average over 20 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: Kimi K2.5 1423 against MiniMax M2.7 1260, 27.1 points apart on a 0 to 100 scale.
- Output price
- Kimi K2.5 $2.85 against MiniMax M2.7 $1.20 per million output tokens, 2.4x apart.
- Context window
- Kimi K2.5 takes 262K tokens, MiniMax M2.7 205K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Kimi K2.5 | Bars | MiniMax M2.7 | Ties |
|---|---|---|---|---|
| Coding | 9 | 6 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 5 | 1 | ||
| Math | 3 | 0 | ||
| Knowledge | 8 | 1 | ||
| Web design | 6 | 2 | ||
| General | 17 | 3 | ||
| All shared boards | 54 | 13 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index96
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| SWE-bench Verified | 70.8% | Not measured | Only Kimi K2.5 measured |
| SWE-bench Multilingual | 67.3% | Not measured | Only Kimi K2.5 measured |
| LMArena WebDev | 1437 | 1399 | Kimi K2.5 |
| AA Coding Index | 46.8 | 52.6 | MiniMax M2.7 |
| LiveCodeBench (Vals AI) | 83.9% | 79.9% | Kimi K2.5 |
| SWE-bench Verified (Vals AI) | 70.0% | 73.8% | MiniMax M2.7 |
| Vibe Code Bench (Vals AI) | 17.5% | 11.9% | Kimi K2.5 |
| Code migration (Vals AI) | 7.0% | 8.7% | MiniMax M2.7 |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only MiniMax M2.7 measured |
| Terminal-Bench 2.1 (Vals AI) | 42.0% | 48.7% | MiniMax M2.7 |
| SciCode | Not measured | 50.1% | Only MiniMax M2.7 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 39.4% | MiniMax M2.7 |
| Terminal-Bench | 43.2% | 45.1% | MiniMax M2.7 |
| WeirdML | 45.6% | 37.0% | Kimi K2.5 |
| ALE-Bench | 821.6 | 599.3 | Kimi K2.5 |
| LMArena Text: coding | 1483 | 1454 | Kimi K2.5 |
| LMArena Text: software and IT | 1471 | 1446 | Kimi K2.5 |
| LMArena WebDev: React | 1429 | 1388 | Kimi K2.5 |
| LMArena WebDev: HTML | 1426 | 1401 | Kimi K2.5 |
| LMArena WebDev: from an image | 1439 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.5 | 22.8 | Kimi K2.5 |
| Epoch Capabilities Index | 148.1 | 145.8 | Kimi K2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 15.3 | Only MiniMax M2.7 measured |
| Design Arena: agents building web apps | 1136 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building full-stack apps | 1114 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building mobile apps | 1147 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building Android apps | 1118 | Not measured | Only Kimi K2.5 measured |
| Design Arena: agents building Godot games | 1219 | Not measured | Only Kimi K2.5 measured |
| Finance Agent (Vals AI) | 35.8% | 27.9% | Kimi K2.5 |
| Tax Agent Bench (Vals AI) | Not measured | 6.9% | Only MiniMax M2.7 measured |
| Legal Research Bench (Vals AI) | 15.9% | 10.6% | Kimi K2.5 |
| Excel Modeling Benchmark (Vals AI) | 28.5% | 28.4% | Kimi K2.5 |
| τ²-Bench Telecom | 95.9% | 84.8% | Kimi K2.5 |
| OSWorld | 63.3% | Not measured | Only Kimi K2.5 measured |
| Vending-Bench 2 | $1,198 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| GPQA Diamond | 84.1% | 86.6% | MiniMax M2.7 |
| MMMU Pro (Vals AI) | 84.3% | Not measured | Only Kimi K2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 87.9% | 87.4% | Kimi K2.5 |
| Humanity's Last Exam (Artificial Analysis run) | 30.7% | 29.6% | Kimi K2.5 |
| ARC-AGI | 65.3% | Not measured | Only Kimi K2.5 measured |
| ARC-AGI-2 | 11.8% | Not measured | Only Kimi K2.5 measured |
| SimpleBench | 46.8% | Not measured | Only Kimi K2.5 measured |
| LMArena Text: hard prompts | 1453 | 1422 | Kimi K2.5 |
| LMArena Text: expert | 1466 | 1443 | Kimi K2.5 |
| LMArena Text: hard prompts in English | 1460 | 1441 | Kimi K2.5 |
| LMArena Vision: diagrams | 1282 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: homework | 1297 | Not measured | Only Kimi K2.5 measured |
| Kagi LLM Benchmark | 78.5% | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| AIME | 95.6% | 91.0% | Kimi K2.5 |
| ProofBench | Not measured | 3.0% | Only MiniMax M2.7 measured |
| LMArena Text: math | 1470 | 1421 | Kimi K2.5 |
| LMArena Text: mathematical work | 1473 | 1437 | Kimi K2.5 |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| MMLU Pro | 85.9% | 80.4% | Kimi K2.5 |
| LegalBench (Vals AI) | Not measured | 84.0% | Only MiniMax M2.7 measured |
| CaseLaw (Vals AI) | 58.7% | 60.9% | MiniMax M2.7 |
| CorpFin (Vals AI) | 68.3% | 61.2% | Kimi K2.5 |
| TaxEval (Vals AI) | 74.2% | 66.6% | Kimi K2.5 |
| MortgageTax (Vals AI) | 66.5% | Not measured | Only Kimi K2.5 measured |
| MedQA (Vals AI) | 94.4% | Not measured | Only Kimi K2.5 measured |
| MedCode (Vals AI) | 39.3% | 34.4% | Kimi K2.5 |
| SimpleQA Verified | 34.3% | Not measured | Only Kimi K2.5 measured |
| LMArena Text: science | 1459 | 1416 | Kimi K2.5 |
| LMArena Text: medicine and healthcare | 1448 | 1409 | Kimi K2.5 |
| LMArena Text: legal and government | 1441 | 1403 | Kimi K2.5 |
| LMArena Text: business and finance | 1427 | 1407 | Kimi K2.5 |
| Neither model has a result on the other 5 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index62
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| Design Arena: websites | 1248 | 1243 | Kimi K2.5 |
| Design Arena: UI components | 1234 | 1210 | Kimi K2.5 |
| Design Arena: game dev | 1206 | 1209 | MiniMax M2.7 |
| Design Arena: data viz | 1219 | 1233 | MiniMax M2.7 |
| Design Arena: 3D | 1204 | 1195 | Kimi K2.5 |
| Design Arena: all code categories | 1236 | 1233 | Kimi K2.5 |
| Design Arena: SVG | 1149 | 1137 | Kimi K2.5 |
| Design Arena: ASCII art | 1166 | 1136 | Kimi K2.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index173
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.9% | Not measured | Only Kimi K2.5 measured |
| MedScribe (Vals AI) | 76.4% | 79.9% | MiniMax M2.7 |
| IFBench | 70.2% | 75.7% | MiniMax M2.7 |
| Long context reasoning (AA-LCR) | 78.0% | 78.3% | MiniMax M2.7 |
| Fiction.LiveBench | 86.1% | Not measured | Only Kimi K2.5 measured |
| CL-bench | 19.3% | Not measured | Only Kimi K2.5 measured |
| ExploitBench | Not measured | 13.3% | Only MiniMax M2.7 measured |
| CL-bench Life | 13.2% | Not measured | Only Kimi K2.5 measured |
| LMArena Text | 1445 | 1405 | Kimi K2.5 |
| LMArena Text: instruction following | 1431 | 1405 | Kimi K2.5 |
| LMArena Text: creative writing | 1422 | 1354 | Kimi K2.5 |
| LMArena Vision | 1269 | Not measured | Only Kimi K2.5 measured |
| LMArena Text: English | 1453 | 1426 | Kimi K2.5 |
| LMArena Text: non-English | 1433 | 1382 | Kimi K2.5 |
| LMArena Text: Chinese | 1494 | 1442 | Kimi K2.5 |
| LMArena Text: German | 1441 | 1398 | Kimi K2.5 |
| LMArena Text: Japanese | 1423 | 1260 | Kimi K2.5 |
| LMArena Text: Korean | 1412 | 1314 | Kimi K2.5 |
| LMArena Text: French | 1454 | 1424 | Kimi K2.5 |
| LMArena Text: Spanish | 1450 | 1402 | Kimi K2.5 |
| LMArena Text: Russian | 1435 | 1383 | Kimi K2.5 |
| LMArena Text: Polish | 1445 | 1387 | Kimi K2.5 |
| LMArena Text: multi-turn | 1444 | 1412 | Kimi K2.5 |
| LMArena Text: longer queries | 1445 | 1418 | Kimi K2.5 |
| LMArena Text: writing and language | 1425 | 1376 | Kimi K2.5 |
| LMArena Text: entertainment and media | 1417 | 1360 | Kimi K2.5 |
| LMArena Vision: English | 1274 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: Chinese | 1328 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: reading text | 1276 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: humor | 1284 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: captioning | 1257 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: recognizing things | 1285 | Not measured | Only Kimi K2.5 measured |
| LMArena Vision: creative writing | 1269 | Not measured | Only Kimi K2.5 measured |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2.5 | MiniMax M2.7 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiniMax M2.7 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.7 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.7 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | MoonshotAI Kimi K2.5 | MiniMax M2.7 |
|---|---|---|
| Maker | Moonshot AI | MiniMax |
| Weights | Open weights | Open weights |
| Released | January 27, 2026 | March 18, 2026 |
| Context window | 262K | 205K |
| Input $/Mtok | $0.532 | $0.30 |
| Output $/Mtok | $2.85 | $1.20 |
| Coding index | 38.6 | 36.2 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $0.24 | $0.64 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2.5 better than MiniMax M2.7 for coding?
Pick Kimi K2.5 for coding: it scores 38.6 on the Vibe Coding Index against 36.2 for MiniMax M2.7. Pick MiniMax M2.7 for output tokens 2.4x cheaper ($1.20 vs $2.85 per million) and work measured by AA Coding Index or SWE-bench Verified (Vals AI), where it leads.
Which is cheaper, Kimi K2.5 or MiniMax M2.7?
Kimi K2.5 costs $0.532 per million input tokens and $2.85 per million output tokens; MiniMax M2.7 costs $0.30 and $1.20. Per solved SWE-bench Verified task, Kimi K2.5 costs $0.24 and MiniMax M2.7 $0.64.
Which has the bigger context window, Kimi K2.5 or MiniMax M2.7?
Kimi K2.5, with 262K tokens against 205K.
How many benchmarks is the Kimi K2.5 vs MiniMax M2.7 comparison based on?
67 benchmarks have a result for both models as of October 22, 2026. Kimi K2.5's coding index rests on 3 independent benchmarks and MiniMax M2.7's on 3. Where only one model has a result, the page says so instead of naming a winner.