# MiniMax-M2.1 vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 3.8× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-1-vs-muse-spark-1-2
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. MiniMax-M2.1 scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 15.8.
- The biggest single-benchmark swing is NYT Connections (extended): 11.2% for MiniMax-M2.1 and 79.2% for Muse Spark 1.2.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 38.4 | 49.8 |
| Rank | 177 | 44 |
| Context | 205K | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $1.20 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.1: 40.1 (#132)
- Muse Spark 1.2: 48.6 (#49)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1384 | 1532 |
| LMArena Coding | 1421 | 1497 |
| DeepSWE | — | 54.9% |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| ALE-Bench | 623.83 | — |

## Agentic & Tool Use

- MiniMax-M2.1: 27.7 (#91)
- Muse Spark 1.2: 29.5 (#77)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- MiniMax-M2.1: 15.8 (#301)
- Muse Spark 1.2: 50.4 (#32)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 11.2% | 79.2% |
| LMArena Hard Prompts | 1410 | 1490 |
| SimpleBench | — | 74.5% |
| CritPt | — | 17.7% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 155.18 |

## Math

- MiniMax-M2.1: 35.6 (#142)
- Muse Spark 1.2: 43.8 (#68)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | 1396 | — |

## Knowledge

- MiniMax-M2.1: 37.7 (#143)
- Muse Spark 1.2: 53.9 (#49)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1432 | 1485 |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 11.8% | — |

## Multimodal

- MiniMax-M2.1: —
- Muse Spark 1.2: 42.6 (#24)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1304 |

## Multilingual

- MiniMax-M2.1: 50.2 (#123)
- Muse Spark 1.2: 57.4 (#10)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1378 | 1479 |
| LMArena Chinese | 1430 | 1519 |
| LMArena Russian | 1386 | 1494 |
| LMArena French | 1405 | — |
| LMArena German | 1380 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1297 | — |
| LMArena Spanish | 1396 | — |

## Instruction Following

- MiniMax-M2.1: 74.0 (#108)
- Muse Spark 1.2: 77.1 (#30)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1466 |

## Long Context

- MiniMax-M2.1: 43.2 (#98)
- Muse Spark 1.2: 45.4 (#35)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1416 | 1483 |

## Writing & Preference

- MiniMax-M2.1: 58.5 (#114)
- Muse Spark 1.2: 72.6 (#14)

| Benchmark | MiniMax-M2.1 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1392 | 1486 |
| LMArena Creative Writing | 1362 | 1444 |
| LMArena Multi-Turn | 1396 | 1504 |
| EQ-Bench Creative Writing | — | 1840 |

## FAQ

### Is MiniMax-M2.1 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 38.4 on the Noometry Index. MiniMax-M2.1 costs 3.8× 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, MiniMax-M2.1 or Muse Spark 1.2?

MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is MiniMax-M2.1 or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 40.1 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 205K.

### How many benchmarks do MiniMax-M2.1 and Muse Spark 1.2 share?

13 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Muse Spark 1.2 has 28.