Model comparison
MiMo-V2.6-Pro vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index. MiMo-V2.6-Pro costs 3.7× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 3 categories and Muse Spark 1.3 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 54.5.
- The biggest single-benchmark swing is ProofBench: 70% for MiMo-V2.6-Pro and 58% for Muse Spark 1.3.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- MiMo-V2.6-Pro has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2.6-Pro | Muse Spark 1.3 | |
|---|---|---|
| Provider | Xiaomi | Meta |
| Noometry Index | 50.3 | 54.8 |
| Released | 2026-09-21 | 2026-09-02 |
| 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 | 19 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
MiMo-V2.6-Pro: 55.5 (#23), Muse Spark 1.3: 56.6 (#21)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1629 | 1657 |
| SciCode | 60.9% | 59.7% |
| LMArena Coding | 1534 | 1514 |
| CursorBench | — | 41.6% |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use Muse Spark 1.3 leads
MiMo-V2.6-Pro: 37.5 (#35), Muse Spark 1.3: 38.6 (#30)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 59.5% | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
MiMo-V2.6-Pro: 43.1 (#50), Muse Spark 1.3: 54.0 (#27)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| CritPt | 26.6% | 26% |
| LMArena Hard Prompts | 1512 | 1503 |
| NYT Connections (extended) | — | 85.1% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.75 |
Math Muse Spark 1.3 leads
MiMo-V2.6-Pro: 54.5 (#45), Muse Spark 1.3: 73.1 (#21)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| ProofBench | 70% | 58% |
| LMArena Math | 1494 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |
Knowledge Too close to call
MiMo-V2.6-Pro: 43.5 (#92), Muse Spark 1.3: 42.6 (#95)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1543 | 1516 |
Multimodal Muse Spark 1.3 leads
MiMo-V2.6-Pro: 40.8 (#43), Muse Spark 1.3: 43.7 (#22)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1264 | 1309 |
| LMArena Document | — | 1471 |
Multilingual Too close to call
MiMo-V2.6-Pro: 56.9 (#14), Muse Spark 1.3: 57.4 (#8)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1474 | 1481 |
| LMArena Chinese | 1529 | 1529 |
| LMArena Russian | 1480 | 1490 |
| LMArena French | — | 1524 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Spanish | — | 1490 |
Instruction Following Too close to call
MiMo-V2.6-Pro: 78.2 (#12), Muse Spark 1.3: 77.5 (#22)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1493 | 1477 |
Long Context Too close to call
MiMo-V2.6-Pro: 46.0 (#27), Muse Spark 1.3: 45.6 (#32)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1501 | 1488 |
Writing & Preference Muse Spark 1.3 leads
MiMo-V2.6-Pro: 66.8 (#33), Muse Spark 1.3: 73.6 (#9)
| Benchmark | MiMo-V2.6-Pro | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1492 | 1490 |
| LMArena Creative Writing | 1468 | 1455 |
| LMArena Multi-Turn | 1464 | 1482 |
| EQ-Bench Creative Writing | — | 1906 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.3 on the Noometry Index. MiMo-V2.6-Pro costs 3.7× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.6-Pro or Muse Spark 1.3?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is MiMo-V2.6-Pro or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do MiMo-V2.6-Pro and Muse Spark 1.3 share?
18 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Muse Spark 1.3 has 37.