Model comparison
MiniMax-M2.1 vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.3 to 38.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
MiniMax
MetaSummary
- They share 16 benchmarks with published results for both. MiniMax-M2.1 scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 37.7.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.1 | Muse Spark | |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 38.4 | 50.3 |
| Released | 2025-12-23 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
MiniMax-M2.1: 40.1 (#132), Muse Spark: 45.6 (#65)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Coding | 1421 | 1482 |
| LMArena WebDev | 1384 | — |
| SciCode | — | 51.5% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.7 (#91), Muse Spark: —
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Muse Spark leads
MiniMax-M2.1: 15.8 (#301), Muse Spark: 34.9 (#61)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1410 | 1475 |
| NYT Connections (extended) | 11.2% | — |
| CritPt | — | 11.3% |
| Epoch Capabilities Index | — | 152.09 |
Math Muse Spark leads
MiniMax-M2.1: 35.6 (#142), Muse Spark: 46.8 (#57)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Math | 1396 | 1455 |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 17% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Muse Spark leads
MiniMax-M2.1: 37.7 (#143), Muse Spark: 65.7 (#12)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Expert | 1432 | 1458 |
| GPQA Diamond | — | 89.8% |
| Humanity's Last Exam | — | 40.6% |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Not comparable
MiniMax-M2.1: —, Muse Spark: 42.7 (#23)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
MiniMax-M2.1: 50.2 (#123), Muse Spark: 56.3 (#23)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1378 | 1464 |
| LMArena Chinese | 1430 | 1507 |
| LMArena French | 1405 | 1497 |
| LMArena German | 1380 | 1497 |
| LMArena Korean | 1297 | 1457 |
| LMArena Russian | 1386 | 1467 |
| LMArena Spanish | 1396 | 1471 |
| LMArena Japanese | 1287 | — |
Instruction Following Muse Spark leads
MiniMax-M2.1: 74.0 (#108), Muse Spark: 76.1 (#47)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1399 | 1443 |
Long Context Muse Spark leads
MiniMax-M2.1: 43.2 (#98), Muse Spark: 44.4 (#65)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1416 | 1451 |
Writing & Preference Muse Spark leads
MiniMax-M2.1: 58.5 (#114), Muse Spark: 66.2 (#37)
| Benchmark | MiniMax-M2.1 | Muse Spark |
|---|---|---|
| LMArena Text | 1392 | 1474 |
| LMArena Creative Writing | 1362 | 1460 |
| LMArena Multi-Turn | 1396 | 1477 |
Frequently asked questions
Is MiniMax-M2.1 better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.3 to 38.4 on the Noometry Index.
Is MiniMax-M2.1 or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 40.1 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Muse Spark share?
16 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Muse Spark has 27.