MiniMax M2.7 vs MiMo-V2.5-Pro
MiniMax M2.7 leads MiMo-V2.5-Pro on coding, 36.2 to 31.6 on the Vibe Coding Index, and MiMo-V2.5-Pro costs 1.3x less per output token ($0.9152 vs $1.20 per million). Updated October 22, 2026; 67 benchmarks have a result for both.
MiniMax M2.7 or MiMo-V2.5-Pro: which to pick
Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro, though on 3 benchmarks against 4.
Pick MiMo-V2.5-Pro for output tokens 1.3x cheaper ($0.9152 vs $1.20 per million) and a lower cost per solved task ($0.03 against $0.64).
- Shared results
- 67
- MiniMax M2.7 only
- 7
- MiMo-V2.5-Pro only
- 3
- 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
MiniMax M2.7
MiniMax M2.7 scores 36.2 against 31.6.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 26.0 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 21.3 against 15.3.
Same board, both measured
Reasoning
GPQA Diamond
MiniMax M2.7
MiniMax M2.7 leads, 86.6% against 82.6%.
Same board, both measured
Math
AIME
No call
Only MiniMax M2.7 has a AIME result, 91.0%.
Directional only
Knowledge
MMLU Pro
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 84.6% against 80.4%.
Same board, both measured
Web design
Design Arena: websites
MiMo-V2.5-Pro
MiMo-V2.5-Pro leads, 1266 against 1243.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5-Pro
MiMo-V2.5-Pro takes 1.05M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.7
MiniMax M2.7 $0.0009, MiMo-V2.5-Pro $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiMo-V2.5-Pro
MiniMax M2.7 $0.64, MiMo-V2.5-Pro $0.03.
Published attempt cost and pass rate
At a glance
- Coding index
- MiniMax M2.7 36.2 from 3 benchmarks, MiMo-V2.5-Pro 31.6 from 4 benchmarks.
- Widest category
- Math, 12.7 points apart on average over 3 shared benchmarks.
- Widest single gap
- Excel Modeling Benchmark (Vals AI): MiniMax M2.7 28.4% against MiMo-V2.5-Pro 55.2%, 26.8 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.7 $1.20 against MiMo-V2.5-Pro $0.9152 per million output tokens, 1.3x apart.
- Context window
- MiniMax M2.7 takes 205K tokens, MiMo-V2.5-Pro 1.05M.
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 | MiniMax M2.7 | Bars | MiMo-V2.5-Pro | Ties |
|---|---|---|---|---|
| Coding | 0 | 14 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 6 | ||
| Reasoning | 2 | 4 | ||
| Math | 0 | 3 | ||
| Knowledge | 2 | 7 | ||
| Web design | 0 | 8 | ||
| General | 0 | 20 | ||
| All shared boards | 4 | 63 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index014
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| LMArena WebDev | 1399 | 1480 | MiMo-V2.5-Pro |
| AA Coding Index | 52.6 | 60.2 | MiMo-V2.5-Pro |
| LiveCodeBench (Vals AI) | 79.9% | 81.3% | MiMo-V2.5-Pro |
| SWE-bench Verified (Vals AI) | 73.8% | 74.0% | MiMo-V2.5-Pro |
| Terminal-Bench 4 (Vals AI) | Not measured | 0.5% | Only MiMo-V2.5-Pro measured |
| Vibe Code Bench (Vals AI) | 11.9% | 34.1% | MiMo-V2.5-Pro |
| Code migration (Vals AI) | 8.7% | 21.6% | MiMo-V2.5-Pro |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only MiniMax M2.7 measured |
| Terminal-Bench 2.1 (Vals AI) | 48.7% | 57.3% | MiMo-V2.5-Pro |
| SciCode | 50.1% | 50.6% | MiMo-V2.5-Pro |
| Terminal-Bench Hard (Artificial Analysis run) | 39.4% | 43.2% | MiMo-V2.5-Pro |
| Terminal-Bench | 45.1% | Not measured | Only MiniMax M2.7 measured |
| WeirdML | 37.0% | Not measured | Only MiniMax M2.7 measured |
| ALE-Bench | 599.3 | 899.8 | MiMo-V2.5-Pro |
| LMArena Text: coding | 1454 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: software and IT | 1446 | 1495 | MiMo-V2.5-Pro |
| LMArena WebDev: React | 1388 | 1469 | MiMo-V2.5-Pro |
| LMArena WebDev: HTML | 1401 | 1473 | MiMo-V2.5-Pro |
| Neither model has a result on the other 21 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 26.0 | MiMo-V2.5-Pro |
| Epoch Capabilities Index | 145.8 | Not measured | Only MiniMax M2.7 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AA Agentic Index | 15.3 | 21.3 | MiMo-V2.5-Pro |
| Finance Agent (Vals AI) | 27.9% | 41.5% | MiMo-V2.5-Pro |
| Tax Agent Bench (Vals AI) | 6.9% | 11.5% | MiMo-V2.5-Pro |
| Legal Research Bench (Vals AI) | 10.6% | 15.9% | MiMo-V2.5-Pro |
| Excel Modeling Benchmark (Vals AI) | 28.4% | 55.2% | MiMo-V2.5-Pro |
| τ²-Bench Telecom | 84.8% | 94.2% | MiMo-V2.5-Pro |
| Neither model has a result on the other 35 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| GPQA Diamond | 86.6% | 82.6% | MiniMax M2.7 |
| GPQA Diamond (Artificial Analysis run) | 87.4% | 86.6% | MiniMax M2.7 |
| Humanity's Last Exam (Artificial Analysis run) | 29.6% | 35.7% | MiMo-V2.5-Pro |
| LMArena Text: hard prompts | 1422 | 1486 | MiMo-V2.5-Pro |
| LMArena Text: expert | 1443 | 1501 | MiMo-V2.5-Pro |
| LMArena Text: hard prompts in English | 1441 | 1494 | MiMo-V2.5-Pro |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| AIME | 91.0% | Not measured | Only MiniMax M2.7 measured |
| ProofBench | 3.0% | 22.0% | MiMo-V2.5-Pro |
| LMArena Text: math | 1421 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: mathematical work | 1437 | 1491 | MiMo-V2.5-Pro |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index27
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MMLU Pro | 80.4% | 84.6% | MiMo-V2.5-Pro |
| LegalBench (Vals AI) | 84.0% | 77.1% | MiniMax M2.7 |
| CaseLaw (Vals AI) | 60.9% | Not measured | Only MiniMax M2.7 measured |
| CorpFin (Vals AI) | 61.2% | 61.4% | MiMo-V2.5-Pro |
| TaxEval (Vals AI) | 66.6% | 73.8% | MiMo-V2.5-Pro |
| MedCode (Vals AI) | 34.4% | 32.5% | MiniMax M2.7 |
| LMArena Text: science | 1416 | 1482 | MiMo-V2.5-Pro |
| LMArena Text: medicine and healthcare | 1409 | 1473 | MiMo-V2.5-Pro |
| LMArena Text: legal and government | 1403 | 1474 | MiMo-V2.5-Pro |
| LMArena Text: business and finance | 1407 | 1466 | MiMo-V2.5-Pro |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| Design Arena: websites | 1243 | 1266 | MiMo-V2.5-Pro |
| Design Arena: UI components | 1210 | 1246 | MiMo-V2.5-Pro |
| Design Arena: game dev | 1209 | 1261 | MiMo-V2.5-Pro |
| Design Arena: data viz | 1233 | 1257 | MiMo-V2.5-Pro |
| Design Arena: 3D | 1195 | 1243 | MiMo-V2.5-Pro |
| Design Arena: all code categories | 1233 | 1265 | MiMo-V2.5-Pro |
| Design Arena: SVG | 1137 | 1181 | MiMo-V2.5-Pro |
| Design Arena: ASCII art | 1136 | 1156 | MiMo-V2.5-Pro |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 79.9% | 83.7% | MiMo-V2.5-Pro |
| IFBench | 75.7% | 79.9% | MiMo-V2.5-Pro |
| Long context reasoning (AA-LCR) | 78.3% | 79.7% | MiMo-V2.5-Pro |
| DTBench | Not measured | 84.5% | Only MiMo-V2.5-Pro measured |
| LMCA | Not measured | 29.5% | Only MiMo-V2.5-Pro measured |
| ExploitBench | 13.3% | Not measured | Only MiniMax M2.7 measured |
| LMArena Text | 1405 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: instruction following | 1405 | 1475 | MiMo-V2.5-Pro |
| LMArena Text: creative writing | 1354 | 1438 | MiMo-V2.5-Pro |
| LMArena Text: English | 1426 | 1477 | MiMo-V2.5-Pro |
| LMArena Text: non-English | 1382 | 1448 | MiMo-V2.5-Pro |
| LMArena Text: Chinese | 1442 | 1507 | MiMo-V2.5-Pro |
| LMArena Text: German | 1398 | 1459 | MiMo-V2.5-Pro |
| LMArena Text: Japanese | 1260 | 1410 | MiMo-V2.5-Pro |
| LMArena Text: Korean | 1314 | 1435 | MiMo-V2.5-Pro |
| LMArena Text: French | 1424 | 1487 | MiMo-V2.5-Pro |
| LMArena Text: Spanish | 1402 | 1469 | MiMo-V2.5-Pro |
| LMArena Text: Russian | 1383 | 1449 | MiMo-V2.5-Pro |
| LMArena Text: Polish | 1387 | 1464 | MiMo-V2.5-Pro |
| LMArena Text: multi-turn | 1412 | 1476 | MiMo-V2.5-Pro |
| LMArena Text: longer queries | 1418 | 1481 | MiMo-V2.5-Pro |
| LMArena Text: writing and language | 1376 | 1451 | MiMo-V2.5-Pro |
| LMArena Text: entertainment and media | 1360 | 1438 | MiMo-V2.5-Pro |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.7 | MiMo-V2.5-Pro | 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 | MiniMax M2.7 | Xiaomi MiMo-V2.5-Pro |
|---|---|---|
| Maker | MiniMax | Xiaomi |
| Weights | Open weights | Open weights |
| Released | March 18, 2026 | April 22, 2026 |
| Context window | 205K | 1.05M |
| Input $/Mtok | $0.30 | $0.4575 |
| Output $/Mtok | $1.20 | $0.9152 |
| Coding index | 36.2 | 31.6 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.64 | $0.03 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.7 better than MiMo-V2.5-Pro for coding?
Pick MiniMax M2.7 for coding: it scores 36.2 on the Vibe Coding Index against 31.6 for MiMo-V2.5-Pro, though on 3 benchmarks against 4. Pick MiMo-V2.5-Pro for output tokens 1.3x cheaper ($0.9152 vs $1.20 per million) and a lower cost per solved task ($0.03 against $0.64).
Which is cheaper, MiniMax M2.7 or MiMo-V2.5-Pro?
MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; MiMo-V2.5-Pro costs $0.4575 and $0.9152. Per solved SWE-bench Verified task, MiniMax M2.7 costs $0.64 and MiMo-V2.5-Pro $0.03.
Which has the bigger context window, MiniMax M2.7 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro, with 1.05M tokens against 205K.
How many benchmarks is the MiniMax M2.7 vs MiMo-V2.5-Pro comparison based on?
67 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.7's coding index rests on 3 independent benchmarks and MiMo-V2.5-Pro's on 4. Where only one model has a result, the page says so instead of naming a winner.