# MiniMax-M2 vs Muse Spark 1.3

> Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 36.9 on the Noometry Index. MiniMax-M2 costs 3.8× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/minimax-m2-vs-muse-spark-1-3
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. MiniMax-M2 scores higher in 0 categories and Muse Spark 1.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 34.6.
- The biggest single-benchmark swing is NYT Connections (extended): 14.8% for MiniMax-M2 and 85.1% for Muse Spark 1.3.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 205K.
- MiniMax-M2 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 36.9 | 54.4 |
| Rank | 201 | 27 |
| Context | 205K | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $1.20 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2: 39.1 (#151)
- Muse Spark 1.3: 56.1 (#18)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1297 | 1655 |
| LMArena Coding | 1370 | 1516 |
| SWE-bench Verified (bash only) | 61% | — |
| CursorBench | — | 41.6% |
| SciCode | — | 59.7% |

## Agentic & Tool Use

- MiniMax-M2: 24.9 (#102)
- Muse Spark 1.3: 38.6 (#28)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 30% | — |
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
| Vending-Bench 2 | 160.6 | — |

## Reasoning

- MiniMax-M2: 18.6 (#256)
- Muse Spark 1.3: 52.9 (#27)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 14.8% | 85.1% |
| LMArena Hard Prompts | 1357 | 1503 |
| Kagi LLM Benchmark | 57.8% | — |
| CritPt | — | 24.9% |
| Chess Puzzles | — | 38% |
| Mystery Game Puzzles | — | 25% |
| DTBench | — | 96.5% |
| LMCA | — | 53.9% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 156.89 |

## Math

- MiniMax-M2: 34.6 (#158)
- Muse Spark 1.3: 72.4 (#16)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Math | 1350 | 1497 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 99.2% |

## Knowledge

- MiniMax-M2: 36.3 (#160)
- Muse Spark 1.3: 42.0 (#92)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1336 | 1516 |

## Multimodal

- MiniMax-M2: —
- Muse Spark 1.3: 43.0 (#21)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1310 |
| LMArena Document | — | 1471 |

## Multilingual

- MiniMax-M2: 45.6 (#165)
- Muse Spark 1.3: 57.8 (#6)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1314 | 1485 |
| LMArena Chinese | 1367 | 1527 |
| LMArena French | 1336 | 1534 |
| LMArena Russian | 1332 | 1491 |
| LMArena Spanish | 1326 | 1485 |
| LMArena German | 1366 | — |
| LMArena Korean | — | 1513 |

## Instruction Following

- MiniMax-M2: 70.4 (#160)
- Muse Spark 1.3: 77.8 (#14)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1329 | 1481 |

## Long Context

- MiniMax-M2: 40.5 (#148)
- Muse Spark 1.3: 45.7 (#29)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1332 | 1491 |

## Writing & Preference

- MiniMax-M2: 53.3 (#157)
- Muse Spark 1.3: 73.7 (#10)

| Benchmark | MiniMax-M2 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1340 | 1490 |
| LMArena Creative Writing | 1288 | 1450 |
| LMArena Multi-Turn | 1362 | 1486 |
| EQ-Bench Creative Writing | — | 1906 |

## FAQ

### Is MiniMax-M2 better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 36.9 on the Noometry Index. MiniMax-M2 costs 3.8× 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, MiniMax-M2 or Muse Spark 1.3?

MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.

### Is MiniMax-M2 or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 205K.

### How many benchmarks do MiniMax-M2 and Muse Spark 1.3 share?

16 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Muse Spark 1.3 has 34.