Qwen3.7 Plus vs MiMo-V2.5
MiMo-V2.5 leads Qwen3.7 Plus on coding, 50.0 to 33.2 on the Vibe Coding Index, and MiMo-V2.5 costs 3.8x less per output token ($0.336 vs $1.28 per million). Updated October 21, 2026; 64 benchmarks have a result for both.
Qwen3.7 Plus or MiMo-V2.5: which to pick
Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus.
Pick Qwen3.7 Plus for work measured by Vibe Code Bench (Vals AI) or SciCode, where it leads.
- Shared results
- 64
- Qwen3.7 Plus only
- 11
- MiMo-V2.5 only
- 16
- 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
MiMo-V2.5
MiMo-V2.5 scores 50.0 against 33.2.
2 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.7 Plus
Qwen3.7 Plus leads, 25.2 against 21.8.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.7 Plus
Qwen3.7 Plus leads, 17.5 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiMo-V2.5 has a GPQA Diamond result, 81.6%.
Directional only
Knowledge
MMLU Pro
No call
Only MiMo-V2.5 has a MMLU Pro result, 82.9%.
Directional only
Web design
Design Arena: websites
Qwen3.7 Plus
Qwen3.7 Plus leads, 1269 against 1266.
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 Plus $0.0010, MiMo-V2.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiMo-V2.5 has the number, $0.01.
Directional only
At a glance
- Coding index
- Qwen3.7 Plus 33.2 from 2 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- General, 5.3 points apart on average over 27 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: Qwen3.7 Plus 1412 against MiMo-V2.5 1306, 17.6 points apart on a 0 to 100 scale.
- Output price
- Qwen3.7 Plus $1.28 against MiMo-V2.5 $0.336 per million output tokens, 3.8x apart.
- Context window
- Qwen3.7 Plus 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 Plus | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 5 | 3 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 5 | 1 | ||
| Reasoning | 6 | 1 | ||
| Math | 2 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 8 | 0 | ||
| General | 25 | 1 | 1 tie | |
| All shared boards | 57 | 6 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index53
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1438 | Only MiMo-V2.5 measured |
| AA Coding Index | 55.9 | 56.8 | MiMo-V2.5 |
| LiveCodeBench (Vals AI) | Not measured | 81.5% | Only MiMo-V2.5 measured |
| SWE-bench Verified (Vals AI) | Not measured | 71.0% | Only MiMo-V2.5 measured |
| Vibe Code Bench (Vals AI) | 46.4% | 42.2% | Qwen3.7 Plus |
| Code migration (Vals AI) | 12.9% | 14.2% | MiMo-V2.5 |
| Terminal-Bench 2.1 (Vals AI) | 52.8% | 60.7% | MiMo-V2.5 |
| SkillsBench (Vals AI) | 54.3% | Not measured | Only Qwen3.7 Plus measured |
| SciCode | 46.1% | 43.9% | Qwen3.7 Plus |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 41.7% | Qwen3.7 Plus |
| FrontierCode | 10.2% | Not measured | Only Qwen3.7 Plus measured |
| ALE-Bench | Not measured | 514.0 | Only MiMo-V2.5 measured |
| LMArena Text: coding | 1473 | 1469 | Qwen3.7 Plus |
| LMArena Text: software and IT | 1473 | 1463 | Qwen3.7 Plus |
| LMArena WebDev: React | Not measured | 1425 | Only MiMo-V2.5 measured |
| LMArena WebDev: HTML | Not measured | 1429 | Only MiMo-V2.5 measured |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 25.2 | 21.8 | Qwen3.7 Plus |
| Epoch Capabilities Index | 147.0 | Not measured | Only Qwen3.7 Plus measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index51
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 17.5 | 15.8 | Qwen3.7 Plus |
| Finance Agent (Vals AI) | 38.2% | 36.7% | Qwen3.7 Plus |
| Tax Agent Bench (Vals AI) | 10.5% | 7.8% | Qwen3.7 Plus |
| Legal Research Bench (Vals AI) | 16.4% | 9.1% | Qwen3.7 Plus |
| Excel Modeling Benchmark (Vals AI) | 49.3% | 55.1% | MiMo-V2.5 |
| τ²-Bench Telecom | 93.0% | 90.6% | Qwen3.7 Plus |
| OSWorld 2.0 | 2.8% | Not measured | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 81.6% | Only MiMo-V2.5 measured |
| MMMU Pro (Vals AI) | Not measured | 80.0% | Only MiMo-V2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 90.0% | 84.9% | Qwen3.7 Plus |
| Humanity's Last Exam (Artificial Analysis run) | 35.6% | 27.2% | Qwen3.7 Plus |
| GPQA Diamond (Epoch AI run) | 87.9% | Not measured | Only Qwen3.7 Plus measured |
| Mystery game puzzles | 17.0% | Not measured | Only Qwen3.7 Plus measured |
| LMArena Text: hard prompts | 1460 | 1450 | Qwen3.7 Plus |
| LMArena Text: expert | 1466 | 1459 | Qwen3.7 Plus |
| LMArena Text: hard prompts in English | 1460 | 1461 | MiMo-V2.5 |
| LMArena Vision: diagrams | 1292 | 1269 | Qwen3.7 Plus |
| LMArena Vision: homework | 1295 | 1262 | Qwen3.7 Plus |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 93.3% | Not measured | Only Qwen3.7 Plus measured |
| FrontierMath, tiers 1 to 3 | 34.4% | Not measured | Only Qwen3.7 Plus measured |
| ProofBench | Not measured | 16.0% | Only MiMo-V2.5 measured |
| LMArena Text: math | 1467 | 1436 | Qwen3.7 Plus |
| LMArena Text: mathematical work | 1470 | 1451 | Qwen3.7 Plus |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 82.9% | Only MiMo-V2.5 measured |
| LegalBench (Vals AI) | Not measured | 78.9% | Only MiMo-V2.5 measured |
| CorpFin (Vals AI) | Not measured | 59.9% | Only MiMo-V2.5 measured |
| TaxEval (Vals AI) | Not measured | 71.8% | Only MiMo-V2.5 measured |
| MortgageTax (Vals AI) | 66.2% | 59.3% | Qwen3.7 Plus |
| MedCode (Vals AI) | Not measured | 31.9% | Only MiMo-V2.5 measured |
| LMArena Text: science | 1464 | 1440 | Qwen3.7 Plus |
| LMArena Text: medicine and healthcare | 1464 | 1432 | Qwen3.7 Plus |
| LMArena Text: legal and government | 1451 | 1425 | Qwen3.7 Plus |
| LMArena Text: business and finance | 1435 | 1432 | Qwen3.7 Plus |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1269 | 1266 | Qwen3.7 Plus |
| Design Arena: UI components | 1261 | 1258 | Qwen3.7 Plus |
| Design Arena: game dev | 1262 | 1249 | Qwen3.7 Plus |
| Design Arena: data viz | 1276 | 1249 | Qwen3.7 Plus |
| Design Arena: 3D | 1239 | 1216 | Qwen3.7 Plus |
| Design Arena: all code categories | 1269 | 1260 | Qwen3.7 Plus |
| Design Arena: SVG | 1208 | 1178 | Qwen3.7 Plus |
| Design Arena: ASCII art | 1143 | 1140 | Qwen3.7 Plus |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index251
| Benchmark | Qwen3.7 Plus | MiMo-V2.5 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 39.3% | 43.3% | MiMo-V2.5 |
| MedScribe (Vals AI) | Not measured | 72.2% | Only MiMo-V2.5 measured |
| Vals Multimodal Index | 53.9% | 52.8% | Qwen3.7 Plus |
| IFBench | 78.0% | 67.1% | Qwen3.7 Plus |
| Long context reasoning (AA-LCR) | 73.0% | 73.0% | Tie |
| DTBench | 84.0% | Not measured | Only Qwen3.7 Plus measured |
| LMCA | 37.6% | Not measured | Only Qwen3.7 Plus measured |
| LMArena Text | 1454 | 1428 | Qwen3.7 Plus |
| LMArena Text: instruction following | 1439 | 1435 | Qwen3.7 Plus |
| LMArena Text: creative writing | 1438 | 1393 | Qwen3.7 Plus |
| LMArena Vision | 1278 | 1247 | Qwen3.7 Plus |
| LMArena Text: English | 1458 | 1447 | Qwen3.7 Plus |
| LMArena Text: non-English | 1445 | 1405 | Qwen3.7 Plus |
| LMArena Text: Chinese | 1509 | 1469 | Qwen3.7 Plus |
| LMArena Text: German | 1471 | 1421 | Qwen3.7 Plus |
| LMArena Text: Japanese | 1412 | 1306 | Qwen3.7 Plus |
| LMArena Text: Korean | 1413 | 1361 | Qwen3.7 Plus |
| LMArena Text: French | 1472 | 1448 | Qwen3.7 Plus |
| LMArena Text: Spanish | 1457 | 1414 | Qwen3.7 Plus |
| LMArena Text: Russian | 1457 | 1396 | Qwen3.7 Plus |
| LMArena Text: Polish | 1449 | 1413 | Qwen3.7 Plus |
| LMArena Text: multi-turn | 1459 | 1445 | Qwen3.7 Plus |
| LMArena Text: longer queries | 1454 | 1445 | Qwen3.7 Plus |
| LMArena Text: writing and language | 1437 | 1409 | Qwen3.7 Plus |
| LMArena Text: entertainment and media | 1422 | 1399 | Qwen3.7 Plus |
| LMArena Vision: English | 1280 | 1259 | Qwen3.7 Plus |
| LMArena Vision: Chinese | 1332 | 1326 | Qwen3.7 Plus |
| LMArena Vision: reading text | 1288 | 1256 | Qwen3.7 Plus |
| LMArena Vision: humor | 1261 | 1226 | Qwen3.7 Plus |
| LMArena Vision: recognizing things | Not measured | 1189 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | 1258 | 1230 | Qwen3.7 Plus |
| LMArena Document | 1444 | Not measured | Only Qwen3.7 Plus measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.7 Plus | 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 Plus | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | Qwen | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | June 3, 2026 | April 22, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $0.32 | $0.168 |
| Output $/Mtok | $1.28 | $0.336 |
| Coding index | 33.2 | 50.0 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | Not computable | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.7 Plus better than MiMo-V2.5 for coding?
Pick MiMo-V2.5 for coding: it scores 50.0 on the Vibe Coding Index against 33.2 for Qwen3.7 Plus. Pick Qwen3.7 Plus for work measured by Vibe Code Bench (Vals AI) or SciCode, where it leads.
Which is cheaper, Qwen3.7 Plus or MiMo-V2.5?
Qwen3.7 Plus costs $0.32 per million input tokens and $1.28 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Cost per solved task is known for MiMo-V2.5 only.
Which has the bigger context window, Qwen3.7 Plus or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.7 Plus vs MiMo-V2.5 comparison based on?
64 benchmarks have a result for both models as of October 21, 2026. Qwen3.7 Plus's coding index rests on 2 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.