Muse Spark 1.1 vs MiMo-V2.5
Muse Spark 1.1 leads MiMo-V2.5 on coding, 70.3 to 50.0 on the Vibe Coding Index, and MiMo-V2.5 costs 12.6x less per output token ($0.336 vs $4.25 per million). Updated October 22, 2026; 73 benchmarks have a result for both.
Muse Spark 1.1 or MiMo-V2.5: which to pick
Pick Muse Spark 1.1 for coding: it scores 70.3 on the Vibe Coding Index against 50.0 for MiMo-V2.5.
Pick MiMo-V2.5 for output tokens 12.6x cheaper ($0.336 vs $4.25 per million) and a lower cost per solved task ($0.01 against $0.43).
- Shared results
- 73
- Muse Spark 1.1 only
- 23
- MiMo-V2.5 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
Muse Spark 1.1
Muse Spark 1.1 scores 70.3 against 50.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
Muse Spark 1.1
Muse Spark 1.1 leads, 33.7 against 21.8.
Same board, both measured
Agentic work
AA Agentic Index
Muse Spark 1.1
Muse Spark 1.1 leads, 25.8 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
Muse Spark 1.1
Muse Spark 1.1 leads, 91.2% against 81.6%.
Same board, both measured
Knowledge
MMLU Pro
Muse Spark 1.1
Muse Spark 1.1 leads, 88.7% against 82.9%.
Same board, both measured
Web design
Design Arena: websites
Muse Spark 1.1
Muse Spark 1.1 leads, 1270 against 1265.
Same board, both measured
Long documents
Listed context window
MiMo-V2.5
MiMo-V2.5 takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiMo-V2.5
Muse Spark 1.1 $0.0034, MiMo-V2.5 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiMo-V2.5
Muse Spark 1.1 $0.43, MiMo-V2.5 $0.01.
Published attempt cost and pass rate
At a glance
- Coding index
- Muse Spark 1.1 70.3 from 3 benchmarks, MiMo-V2.5 50.0 from 3 benchmarks.
- Widest category
- Agentic work, 15.2 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Muse Spark 1.1 72.2% against MiMo-V2.5 42.2%, 30.0 points apart on a 0 to 100 scale.
- Output price
- Muse Spark 1.1 $4.25 against MiMo-V2.5 $0.336 per million output tokens, 12.6x apart.
- Context window
- Muse Spark 1.1 takes 1.05M 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 | Muse Spark 1.1 | Bars | MiMo-V2.5 | Ties |
|---|---|---|---|---|
| Coding | 12 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 9 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 9 | 0 | ||
| Web design | 8 | 0 | ||
| General | 27 | 0 | ||
| All shared boards | 73 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index120
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| LMArena WebDev | 1542 | 1438 | Muse Spark 1.1 |
| AA Coding Index | 71.3 | 56.8 | Muse Spark 1.1 |
| LiveCodeBench (Vals AI) | 85.9% | 81.5% | Muse Spark 1.1 |
| SWE-bench Verified (Vals AI) | 82.0% | 71.0% | Muse Spark 1.1 |
| Vibe Code Bench (Vals AI) | 72.2% | 42.2% | Muse Spark 1.1 |
| Code migration (Vals AI) | 31.1% | 14.2% | Muse Spark 1.1 |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Muse Spark 1.1 measured |
| Terminal-Bench 2.1 (Vals AI) | 69.3% | 60.7% | Muse Spark 1.1 |
| SkillsBench (Vals AI) | 59.2% | Not measured | Only Muse Spark 1.1 measured |
| SciCode | 58.8% | 43.9% | Muse Spark 1.1 |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 41.7% | Only MiMo-V2.5 measured |
| ALE-Bench | Not measured | 514.0 | Only MiMo-V2.5 measured |
| LMArena Text: coding | 1498 | 1469 | Muse Spark 1.1 |
| LMArena Text: software and IT | 1498 | 1463 | Muse Spark 1.1 |
| LMArena WebDev: React | 1532 | 1425 | Muse Spark 1.1 |
| LMArena WebDev: HTML | 1540 | 1429 | Muse Spark 1.1 |
| LMArena WebDev: from an image | 1540 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 21.8 | Muse Spark 1.1 |
| Epoch Capabilities Index | 154.1 | Not measured | Only Muse Spark 1.1 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| AA Agentic Index | 25.8 | 15.8 | Muse Spark 1.1 |
| Design Arena: agents building web apps | 1207 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building full-stack apps | 1199 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building mobile apps | 1175 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building Android apps | 1178 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building Godot games | 1103 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: agents building games | 1183 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: HTML slides | 1195 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: PowerPoint slides | 1155 | Not measured | Only Muse Spark 1.1 measured |
| Design Arena: spreadsheets | 1042 | Not measured | Only Muse Spark 1.1 measured |
| Finance Agent (Vals AI) | 57.2% | 36.7% | Muse Spark 1.1 |
| Tax Agent Bench (Vals AI) | Not measured | 7.8% | Only MiMo-V2.5 measured |
| Legal Research Bench (Vals AI) | 38.0% | 9.1% | Muse Spark 1.1 |
| Excel Modeling Benchmark (Vals AI) | 56.4% | 55.1% | Muse Spark 1.1 |
| Time Horizon Index (Vals AI) | 1.7% | Not measured | Only Muse Spark 1.1 measured |
| τ²-Bench Telecom | Not measured | 90.6% | Only MiMo-V2.5 measured |
| APEX-Agents | 31.8% | Not measured | Only Muse Spark 1.1 measured |
| Vending-Bench 2 | $6,520 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 23 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| GPQA Diamond | 91.2% | 81.6% | Muse Spark 1.1 |
| MMMU Pro (Vals AI) | 86.6% | 80.0% | Muse Spark 1.1 |
| GPQA Diamond (Artificial Analysis run) | 89.8% | 84.9% | Muse Spark 1.1 |
| Humanity's Last Exam (Artificial Analysis run) | 46.2% | 27.2% | Muse Spark 1.1 |
| Chess puzzles | 34.0% | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: hard prompts | 1485 | 1450 | Muse Spark 1.1 |
| LMArena Text: expert | 1478 | 1459 | Muse Spark 1.1 |
| LMArena Text: hard prompts in English | 1480 | 1461 | Muse Spark 1.1 |
| LMArena Vision: diagrams | 1305 | 1269 | Muse Spark 1.1 |
| LMArena Vision: homework | 1287 | 1262 | Muse Spark 1.1 |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| ProofBench | 39.0% | 16.0% | Muse Spark 1.1 |
| LMArena Text: math | 1482 | 1436 | Muse Spark 1.1 |
| LMArena Text: mathematical work | 1487 | 1451 | Muse Spark 1.1 |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| MMLU Pro | 88.7% | 82.9% | Muse Spark 1.1 |
| LegalBench (Vals AI) | 85.0% | 78.9% | Muse Spark 1.1 |
| CorpFin (Vals AI) | 71.3% | 59.9% | Muse Spark 1.1 |
| TaxEval (Vals AI) | 79.7% | 71.8% | Muse Spark 1.1 |
| MortgageTax (Vals AI) | 66.1% | 59.3% | Muse Spark 1.1 |
| MedCode (Vals AI) | Not measured | 31.9% | Only MiMo-V2.5 measured |
| SimpleQA Verified | 57.8% | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text: science | 1484 | 1440 | Muse Spark 1.1 |
| LMArena Text: medicine and healthcare | 1479 | 1432 | Muse Spark 1.1 |
| LMArena Text: legal and government | 1481 | 1425 | Muse Spark 1.1 |
| LMArena Text: business and finance | 1470 | 1432 | Muse Spark 1.1 |
| 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 | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| Design Arena: websites | 1270 | 1265 | Muse Spark 1.1 |
| Design Arena: UI components | 1289 | 1255 | Muse Spark 1.1 |
| Design Arena: game dev | 1269 | 1249 | Muse Spark 1.1 |
| Design Arena: data viz | 1268 | 1250 | Muse Spark 1.1 |
| Design Arena: 3D | 1260 | 1215 | Muse Spark 1.1 |
| Design Arena: all code categories | 1276 | 1260 | Muse Spark 1.1 |
| Design Arena: SVG | 1235 | 1179 | Muse Spark 1.1 |
| Design Arena: ASCII art | 1271 | 1140 | Muse Spark 1.1 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
| Benchmark | Muse Spark 1.1 | MiMo-V2.5 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 61.3% | Not measured | Only Muse Spark 1.1 measured |
| SAGE (Vals AI) | 45.6% | 43.3% | Muse Spark 1.1 |
| MedScribe (Vals AI) | 88.9% | 72.2% | Muse Spark 1.1 |
| Vals Multimodal Index | 66.7% | 52.8% | Muse Spark 1.1 |
| IFBench | Not measured | 67.1% | Only MiMo-V2.5 measured |
| Long context reasoning (AA-LCR) | 77.7% | 73.0% | Muse Spark 1.1 |
| DTBench | 94.4% | Not measured | Only Muse Spark 1.1 measured |
| LMCA | 49.9% | Not measured | Only Muse Spark 1.1 measured |
| Surface Evolver Bench | 52.5% | Not measured | Only Muse Spark 1.1 measured |
| LMArena Text | 1478 | 1428 | Muse Spark 1.1 |
| LMArena Text: instruction following | 1457 | 1435 | Muse Spark 1.1 |
| LMArena Text: creative writing | 1435 | 1393 | Muse Spark 1.1 |
| LMArena Vision | 1293 | 1247 | Muse Spark 1.1 |
| LMArena Text: English | 1478 | 1447 | Muse Spark 1.1 |
| LMArena Text: non-English | 1471 | 1405 | Muse Spark 1.1 |
| LMArena Text: Chinese | 1515 | 1469 | Muse Spark 1.1 |
| LMArena Text: German | 1469 | 1421 | Muse Spark 1.1 |
| LMArena Text: Japanese | 1450 | 1306 | Muse Spark 1.1 |
| LMArena Text: Korean | 1459 | 1361 | Muse Spark 1.1 |
| LMArena Text: French | 1492 | 1448 | Muse Spark 1.1 |
| LMArena Text: Spanish | 1464 | 1414 | Muse Spark 1.1 |
| LMArena Text: Russian | 1482 | 1396 | Muse Spark 1.1 |
| LMArena Text: Polish | 1499 | 1413 | Muse Spark 1.1 |
| LMArena Text: multi-turn | 1484 | 1445 | Muse Spark 1.1 |
| LMArena Text: longer queries | 1462 | 1445 | Muse Spark 1.1 |
| LMArena Text: writing and language | 1448 | 1409 | Muse Spark 1.1 |
| LMArena Text: entertainment and media | 1438 | 1399 | Muse Spark 1.1 |
| LMArena Vision: English | 1292 | 1259 | Muse Spark 1.1 |
| LMArena Vision: Chinese | 1348 | 1326 | Muse Spark 1.1 |
| LMArena Vision: reading text | 1301 | 1256 | Muse Spark 1.1 |
| LMArena Vision: humor | 1288 | 1226 | Muse Spark 1.1 |
| LMArena Vision: recognizing things | Not measured | 1189 | Only MiMo-V2.5 measured |
| LMArena Vision: creative writing | 1253 | 1230 | Muse Spark 1.1 |
| LMArena Document | 1465 | Not measured | Only Muse Spark 1.1 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Muse Spark 1.1 | 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 | Meta Muse Spark 1.1 | Xiaomi MiMo-V2.5 |
|---|---|---|
| Maker | Meta | Xiaomi |
| Weights | No public weights listed | Open weights |
| Released | July 16, 2026 | April 22, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.25 | $0.168 |
| Output $/Mtok | $4.25 | $0.336 |
| Coding index | 70.3 | 50.0 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $0.43 | $0.01 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Muse Spark 1.1 better than MiMo-V2.5 for coding?
Pick Muse Spark 1.1 for coding: it scores 70.3 on the Vibe Coding Index against 50.0 for MiMo-V2.5. Pick MiMo-V2.5 for output tokens 12.6x cheaper ($0.336 vs $4.25 per million) and a lower cost per solved task ($0.01 against $0.43).
Which is cheaper, Muse Spark 1.1 or MiMo-V2.5?
Muse Spark 1.1 costs $1.25 per million input tokens and $4.25 per million output tokens; MiMo-V2.5 costs $0.168 and $0.336. Per solved SWE-bench Verified task, Muse Spark 1.1 costs $0.43 and MiMo-V2.5 $0.01.
Which has the bigger context window, Muse Spark 1.1 or MiMo-V2.5?
MiMo-V2.5, with 1.05M tokens against 1.05M.
How many benchmarks is the Muse Spark 1.1 vs MiMo-V2.5 comparison based on?
73 benchmarks have a result for both models as of October 22, 2026. Muse Spark 1.1'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.