Model comparison
MiMo-V2.5-Pro vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 3.7× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 1 category and Muse Spark 1.2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 25.9.
- The biggest single-benchmark swing is NYT Connections (extended): 34.4% for MiMo-V2.5-Pro and 79.2% for Muse Spark 1.2.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- MiMo-V2.5-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.5-Pro | Muse Spark 1.2 | |
|---|---|---|
| Provider | Xiaomi | Meta |
| Noometry Index | 44.8 | 49.8 |
| Released | 2026-04-22 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.43 | $1.25 |
| Output $ / M tokens | $0.87 | $4.25 |
| Results tracked | 27 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
MiMo-V2.5-Pro: 47.0 (#58), Muse Spark 1.2: 48.6 (#49)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1477 | 1532 |
| SciCode | 50.2% | 56.4% |
| LMArena Coding | 1502 | 1497 |
| DeepSWE | — | 54.9% |
| FrontierSWE | — | 12% |
| WeirdML | — | 60.3% |
| ALE-Bench | 899.8 | — |
Agentic & Tool Use Not comparable
MiMo-V2.5-Pro: —, Muse Spark 1.2: 29.5 (#77)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
MiMo-V2.5-Pro: 25.9 (#124), Muse Spark 1.2: 50.4 (#32)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 34.4% | 79.2% |
| CritPt | 4% | 17.7% |
| LMArena Hard Prompts | 1487 | 1490 |
| DTBench | 84.5% | 94.7% |
| LMCA | 29.5% | 48.4% |
| SimpleBench | — | 74.5% |
| Epoch Capabilities Index | — | 155.18 |
Math Muse Spark 1.2 leads
MiMo-V2.5-Pro: 38.6 (#84), Muse Spark 1.2: 43.8 (#68)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 22% | 43% |
| LMArena Math | 1480 | — |
Knowledge Muse Spark 1.2 leads
MiMo-V2.5-Pro: 41.5 (#100), Muse Spark 1.2: 53.9 (#49)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1501 | 1485 |
| SimpleQA Verified | — | 60.3% |
Multimodal Not comparable
MiMo-V2.5-Pro: —, Muse Spark 1.2: 42.6 (#24)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |
Multilingual Muse Spark 1.2 leads
MiMo-V2.5-Pro: 55.3 (#33), Muse Spark 1.2: 57.4 (#10)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1449 | 1479 |
| LMArena Chinese | 1507 | 1519 |
| LMArena Russian | 1450 | 1494 |
| LMArena French | 1489 | — |
| LMArena German | 1455 | — |
| LMArena Japanese | 1418 | — |
| LMArena Korean | 1436 | — |
| LMArena Spanish | 1470 | — |
Instruction Following Too close to call
MiMo-V2.5-Pro: 77.6 (#21), Muse Spark 1.2: 77.1 (#30)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1477 | 1466 |
Long Context Too close to call
MiMo-V2.5-Pro: 45.4 (#38), Muse Spark 1.2: 45.4 (#35)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1482 | 1483 |
Writing & Preference Muse Spark 1.2 leads
MiMo-V2.5-Pro: 65.5 (#47), Muse Spark 1.2: 72.6 (#14)
| Benchmark | MiMo-V2.5-Pro | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1465 | 1486 |
| LMArena Creative Writing | 1440 | 1444 |
| EQ-Bench Creative Writing | 1493 | 1840 |
| LMArena Multi-Turn | 1477 | 1504 |
| EQ-Bench 4 | 1208 | — |
Frequently asked questions
Is MiMo-V2.5-Pro better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 3.7× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5-Pro or Muse Spark 1.2?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.
Is MiMo-V2.5-Pro or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 47.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do MiMo-V2.5-Pro and Muse Spark 1.2 share?
19 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Muse Spark 1.2 has 28.