Qwen3.7 Max vs MiMo-V2.5
Qwen3.7 Max leads MiMo-V2.5 on coding, 54.1 to 50.0 on the Vibe Coding Index, and MiMo-V2.5 costs 13.2x less per output token ($0.336 vs $4.425 per million). Updated October 22, 2026; 39 benchmarks have a result for both.
Qwen3.7 Max or MiMo-V2.5: which to pick
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 50.0 for MiMo-V2.5.
Pick MiMo-V2.5 for output tokens 13.2x cheaper ($0.336 vs $4.425 per million) and a lower cost per solved task ($0.01 against $4.69).
- Shared results
- 39
- Qwen3.7 Max only
- 20
- MiMo-V2.5 only
- 41
- 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
Qwen3.7 Max
Qwen3.7 Max scores 54.1 against 50.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
Qwen3.7 Max
Qwen3.7 Max leads, 29.5 against 21.8.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.7 Max
Qwen3.7 Max leads, 22.5 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.7 Max
Qwen3.7 Max leads, 90.2% against 81.6%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.7 Max
Qwen3.7 Max leads, 89.3% against 82.9%.
Same board, both measured
Web design
Design Arena: websites
Qwen3.7 Max
Qwen3.7 Max leads, 1274 against 1265.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5
MiMo-V2.5 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
Qwen3.7 Max $0.0037, MiMo-V2.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiMo-V2.5
Qwen3.7 Max $4.69, MiMo-V2.5 $0.01.
Published attempt cost and pass rate
At a glance
- Coding index
- Qwen3.7 Max 54.1 from 3 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- Math, 10.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ALE-Bench: Qwen3.7 Max 1189.4 against MiMo-V2.5 514.0, 22.5 points apart on a 0 to 100 scale.
- Output price
- Qwen3.7 Max $4.425 against MiMo-V2.5 $0.336 per million output tokens, 13.2x apart.
- Context window
- Qwen3.7 Max takes 1M tokens, MiMo-V2.5 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 | Qwen3.7 Max | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 10 | 2 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 6 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 8 | 0 | ||
| General | 3 | 0 | ||
| All shared boards | 37 | 2 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index102
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| LMArena WebDev | 1515 | 1438 | Qwen3.7 Max |
| AA Coding Index | 66.0 | 56.8 | Qwen3.7 Max |
| LiveCodeBench (Vals AI) | 87.1% | 81.5% | Qwen3.7 Max |
| SWE-bench Verified (Vals AI) | 68.8% | 71.0% | MiMo-V2.5 |
| Vibe Code Bench (Vals AI) | 47.7% | 42.2% | Qwen3.7 Max |
| Code migration (Vals AI) | 13.1% | 14.2% | MiMo-V2.5 |
| Terminal-Bench 2.1 (Vals AI) | 61.0% | 60.7% | Qwen3.7 Max |
| SciCode | 49.5% | 43.9% | Qwen3.7 Max |
| Terminal-Bench Hard (Artificial Analysis run) | 50.8% | 41.7% | Qwen3.7 Max |
| ALE-Bench | 1189.4 | 514.0 | Qwen3.7 Max |
| LMArena Text: coding | Not measured | 1469 | Only MiMo-V2.5 measured |
| LMArena Text: software and IT | Not measured | 1463 | Only MiMo-V2.5 measured |
| LMArena WebDev: React | 1514 | 1425 | Qwen3.7 Max |
| LMArena WebDev: HTML | 1512 | 1429 | Qwen3.7 Max |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.5 | 21.8 | Qwen3.7 Max |
| Epoch Capabilities Index | 154.0 | Not measured | Only Qwen3.7 Max measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 22.5 | 15.8 | Qwen3.7 Max |
| Design Arena: agents building web apps | 1208 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building full-stack apps | 1191 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building mobile apps | 1155 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Android apps | 1159 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building Godot games | 1187 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: agents building games | 1161 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: HTML slides | 1108 | Not measured | Only Qwen3.7 Max measured |
| Design Arena: PowerPoint slides | 1171 | Not measured | Only Qwen3.7 Max measured |
| Finance Agent (Vals AI) | 47.8% | 36.7% | Qwen3.7 Max |
| Tax Agent Bench (Vals AI) | 15.8% | 7.8% | Qwen3.7 Max |
| Legal Research Bench (Vals AI) | 25.5% | 9.1% | Qwen3.7 Max |
| Excel Modeling Benchmark (Vals AI) | 57.0% | 55.1% | Qwen3.7 Max |
| τ²-Bench Telecom | 94.7% | 90.6% | Qwen3.7 Max |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 90.2% | 81.6% | Qwen3.7 Max |
| MMMU Pro (Vals AI) | Not measured | 80.0% | Only MiMo-V2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 92.3% | 84.9% | Qwen3.7 Max |
| Humanity's Last Exam (Artificial Analysis run) | 40.5% | 27.2% | Qwen3.7 Max |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only Qwen3.7 Max measured |
| SimpleBench | 70.4% | Not measured | Only Qwen3.7 Max measured |
| Chess puzzles | 26.0% | Not measured | Only Qwen3.7 Max measured |
| Mystery game puzzles | 32.0% | Not measured | Only Qwen3.7 Max measured |
| EBR-bench | 9.5% | Not measured | Only Qwen3.7 Max measured |
| LMArena Text: hard prompts | Not measured | 1450 | Only MiMo-V2.5 measured |
| LMArena Text: expert | Not measured | 1459 | Only MiMo-V2.5 measured |
| LMArena Text: hard prompts in English | Not measured | 1461 | Only MiMo-V2.5 measured |
| LMArena Vision: diagrams | Not measured | 1269 | Only MiMo-V2.5 measured |
| LMArena Vision: homework | Not measured | 1262 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 95.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tiers 1 to 3 | 64.6% | Not measured | Only Qwen3.7 Max measured |
| FrontierMath, tier 4 | 34.1% | Not measured | Only Qwen3.7 Max measured |
| ProofBench | 26.0% | 16.0% | Qwen3.7 Max |
| LMArena Text: math | Not measured | 1436 | Only MiMo-V2.5 measured |
| LMArena Text: mathematical work | Not measured | 1451 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 89.3% | 82.9% | Qwen3.7 Max |
| LegalBench (Vals AI) | 84.9% | 78.9% | Qwen3.7 Max |
| CorpFin (Vals AI) | 63.7% | 59.9% | Qwen3.7 Max |
| TaxEval (Vals AI) | 75.3% | 71.8% | Qwen3.7 Max |
| MortgageTax (Vals AI) | Not measured | 59.3% | Only MiMo-V2.5 measured |
| MedCode (Vals AI) | 38.8% | 31.9% | Qwen3.7 Max |
| SimpleQA Verified | 55.8% | Not measured | Only Qwen3.7 Max measured |
| LMArena Text: science | Not measured | 1440 | Only MiMo-V2.5 measured |
| LMArena Text: medicine and healthcare | Not measured | 1432 | Only MiMo-V2.5 measured |
| LMArena Text: legal and government | Not measured | 1425 | Only MiMo-V2.5 measured |
| LMArena Text: business and finance | Not measured | 1432 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1274 | 1265 | Qwen3.7 Max |
| Design Arena: UI components | 1267 | 1255 | Qwen3.7 Max |
| Design Arena: game dev | 1264 | 1249 | Qwen3.7 Max |
| Design Arena: data viz | 1275 | 1250 | Qwen3.7 Max |
| Design Arena: 3D | 1265 | 1215 | Qwen3.7 Max |
| Design Arena: all code categories | 1275 | 1260 | Qwen3.7 Max |
| Design Arena: SVG | 1216 | 1179 | Qwen3.7 Max |
| Design Arena: ASCII art | 1211 | 1140 | Qwen3.7 Max |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.3% | Only MiMo-V2.5 measured |
| MedScribe (Vals AI) | 79.4% | 72.2% | Qwen3.7 Max |
| Vals Multimodal Index | Not measured | 52.8% | Only MiMo-V2.5 measured |
| IFBench | 80.5% | 67.1% | Qwen3.7 Max |
| Long context reasoning (AA-LCR) | 79.0% | 73.0% | Qwen3.7 Max |
| DTBench | 92.3% | Not measured | Only Qwen3.7 Max measured |
| LMCA | 44.0% | Not measured | Only Qwen3.7 Max measured |
| LMArena Text | Not measured | 1428 | Only MiMo-V2.5 measured |
| LMArena Text: instruction following | Not measured | 1435 | Only MiMo-V2.5 measured |
| LMArena Text: creative writing | Not measured | 1393 | Only MiMo-V2.5 measured |
| LMArena Vision | Not measured | 1247 | Only MiMo-V2.5 measured |
| LMArena Text: English | Not measured | 1447 | Only MiMo-V2.5 measured |
| LMArena Text: non-English | Not measured | 1405 | Only MiMo-V2.5 measured |
| LMArena Text: Chinese | Not measured | 1469 | Only MiMo-V2.5 measured |
| LMArena Text: German | Not measured | 1421 | Only MiMo-V2.5 measured |
| LMArena Text: Japanese | Not measured | 1306 | Only MiMo-V2.5 measured |
| LMArena Text: Korean | Not measured | 1361 | Only MiMo-V2.5 measured |
| LMArena Text: French | Not measured | 1448 | Only MiMo-V2.5 measured |
| LMArena Text: Spanish | Not measured | 1414 | Only MiMo-V2.5 measured |
| LMArena Text: Russian | Not measured | 1396 | Only MiMo-V2.5 measured |
| LMArena Text: Polish | Not measured | 1413 | Only MiMo-V2.5 measured |
| LMArena Text: multi-turn | Not measured | 1445 | Only MiMo-V2.5 measured |
| LMArena Text: longer queries | Not measured | 1445 | Only MiMo-V2.5 measured |
| LMArena Text: writing and language | Not measured | 1409 | Only MiMo-V2.5 measured |
| LMArena Text: entertainment and media | Not measured | 1399 | Only MiMo-V2.5 measured |
| LMArena Vision: English | Not measured | 1259 | Only MiMo-V2.5 measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only MiMo-V2.5 measured |
| LMArena Vision: reading text | Not measured | 1256 | Only MiMo-V2.5 measured |
| LMArena Vision: humor | Not measured | 1226 | Only MiMo-V2.5 measured |
| LMArena Vision: recognizing things | Not measured | 1189 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | Not measured | 1230 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.7 Max | MiMo-V2.5 | 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
MiMo-V2.5 costs less
Repository review
50K input + 3K output tokens
MiMo-V2.5 costs less
Agent loop
200K input + 10K output tokens
MiMo-V2.5 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 | Qwen3.7 Max | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | Qwen | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | May 21, 2026 | April 22, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $1.475 | $0.168 |
| Output $/Mtok | $4.425 | $0.336 |
| Coding index | 54.1 | 50.0 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $4.69 | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.7 Max better than MiMo-V2.5 for coding?
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 50.0 for MiMo-V2.5. Pick MiMo-V2.5 for output tokens 13.2x cheaper ($0.336 vs $4.425 per million) and a lower cost per solved task ($0.01 against $4.69).
Which is cheaper, Qwen3.7 Max or MiMo-V2.5?
Qwen3.7 Max costs $1.475 per million input tokens and $4.425 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Per solved SWE-bench Verified task, Qwen3.7 Max costs $4.69 and MiMo-V2.5 $0.01.
Which has the bigger context window, Qwen3.7 Max or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.7 Max vs MiMo-V2.5 comparison based on?
39 benchmarks have a result for both models as of October 22, 2026. Qwen3.7 Max's coding index rests on 3 independent benchmarks and MiMo-V2.5's on 3. Where only one model has a result, the page says so instead of naming a winner.