Model comparison
MiMo-V2.5-Pro vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.6 to 45.2 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 3 categories and Muse Spark in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 42.2.
- The biggest single-benchmark swing is CritPt: 4% for MiMo-V2.5-Pro and 11.3% for Muse Spark.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | Muse Spark | |
|---|---|---|
| Provider | Xiaomi | Meta |
| Noometry Index | 45.2 | 50.6 |
| Released | 2026-04-22 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.4 (#60), Muse Spark: 46.2 (#69)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| SciCode | 50.2% | 51.5% |
| LMArena Coding | 1503 | 1481 |
| LMArena WebDev | 1479 | — |
| ALE-Bench | 899.8 | — |
Reasoning Muse Spark leads
MiMo-V2.5-Pro: 26.8 (#130), Muse Spark: 35.9 (#67)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| CritPt | 4% | 11.3% |
| LMArena Hard Prompts | 1488 | 1474 |
| NYT Connections (extended) | 34.4% | — |
| DTBench | 84.5% | — |
| LMCA | 29.5% | — |
| Epoch Capabilities Index | — | 152.04 |
Math Muse Spark leads
MiMo-V2.5-Pro: 40.0 (#96), Muse Spark: 47.8 (#66)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| ProofBench | 22% | 17% |
| LMArena Math | 1481 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
MiMo-V2.5-Pro: 42.2 (#98), Muse Spark: 65.7 (#13)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Expert | 1503 | 1457 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Muse Spark: 43.4 (#24)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
MiMo-V2.5-Pro: 55.1 (#34), Muse Spark: 56.1 (#24)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Non-English | 1449 | 1464 |
| LMArena Chinese | 1507 | 1509 |
| LMArena French | 1488 | 1497 |
| LMArena German | 1458 | 1497 |
| LMArena Korean | 1437 | 1459 |
| LMArena Russian | 1450 | 1466 |
| LMArena Spanish | 1471 | 1472 |
| LMArena Japanese | 1412 | — |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), Muse Spark: 75.9 (#51)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1477 | 1442 |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#37), Muse Spark: 44.4 (#69)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1483 | 1451 |
Writing & Preference Too close to call
MiMo-V2.5-Pro: 65.3 (#49), Muse Spark: 66.0 (#39)
| Benchmark | MiMo-V2.5-Pro | Muse Spark |
|---|---|---|
| LMArena Text | 1465 | 1474 |
| LMArena Creative Writing | 1440 | 1459 |
| LMArena Multi-Turn | 1477 | 1477 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.6 to 45.2 on the Noometry Index.
Is MiMo-V2.5-Pro or Muse Spark better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 46.2 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and Muse Spark share?
19 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Muse Spark has 27.