# MiniMax-M3 vs Muse Spark 1.3

> Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 43.5 on the Noometry Index. MiniMax-M3 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-m3-vs-muse-spark-1-3
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. MiniMax-M3 scores higher in 1 category and Muse Spark 1.3 in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 39.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 99.2% for Muse Spark 1.3.
- MiniMax-M3 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 1M.
- MiniMax-M3 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 43.5 | 54.4 |
| Rank | 81 | 27 |
| Context | 1M | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $1.20 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M3: 41.5 (#111)
- Muse Spark 1.3: 56.1 (#18)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1482 | 1655 |
| SciCode | 47.1% | 59.7% |
| LMArena Coding | 1470 | 1516 |
| FrontierCode | 14.7% | — |
| CursorBench | — | 41.6% |
| ALE-Bench | 640.02 | — |

## Agentic & Tool Use

- MiniMax-M3: 22.5 (#121)
- Muse Spark 1.3: 38.6 (#28)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | 37.7% | 57.8% |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | — | 27.6% |
| Vending-Bench 2 | 2,158 | — |

## Reasoning

- MiniMax-M3: 29.3 (#83)
- Muse Spark 1.3: 52.9 (#27)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 65.1% | 85.1% |
| CritPt | 3.7% | 24.9% |
| Chess Puzzles | 14% | 38% |
| LMArena Hard Prompts | 1447 | 1503 |
| Mystery Game Puzzles | 8% | 25% |
| DTBench | 78.9% | 96.5% |
| LMCA | 33.7% | 53.9% |
| Epoch Capabilities Index | 147 | 156.89 |
| SimpleBench | 45.8% | — |
| Surface Evolver Bench | 55% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 61.4 | — |

## Math

- MiniMax-M3: 39.1 (#83)
- Muse Spark 1.3: 72.4 (#16)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 99.2% |
| LMArena Math | 1432 | 1497 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | 18% | — |

## Knowledge

- MiniMax-M3: 58.4 (#32)
- Muse Spark 1.3: 42.0 (#92)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1462 | 1516 |
| GPQA Diamond | 90.9% | — |

## Multimodal

- MiniMax-M3: 39.5 (#45)
- Muse Spark 1.3: 43.0 (#21)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1254 | 1310 |
| LMArena Document | 1435 | 1471 |

## Multilingual

- MiniMax-M3: 53.2 (#70)
- Muse Spark 1.3: 57.8 (#6)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1420 | 1485 |
| LMArena Chinese | 1465 | 1527 |
| LMArena French | 1445 | 1534 |
| LMArena Korean | 1372 | 1513 |
| LMArena Russian | 1430 | 1491 |
| LMArena Spanish | 1431 | 1485 |
| LMArena German | 1424 | — |
| LMArena Japanese | 1381 | — |

## Instruction Following

- MiniMax-M3: 75.7 (#56)
- Muse Spark 1.3: 77.8 (#14)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1481 |

## Long Context

- MiniMax-M3: 44.2 (#68)
- Muse Spark 1.3: 45.7 (#29)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1445 | 1491 |

## Writing & Preference

- MiniMax-M3: 62.3 (#79)
- Muse Spark 1.3: 73.7 (#10)

| Benchmark | MiniMax-M3 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1433 | 1490 |
| LMArena Creative Writing | 1405 | 1450 |
| LMArena Multi-Turn | 1441 | 1486 |
| EQ-Bench Creative Writing | — | 1906 |
| EQ-Bench 4 | 1150 | — |

## FAQ

### Is MiniMax-M3 better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 43.5 on the Noometry Index. MiniMax-M3 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-M3 or Muse Spark 1.3?

MiniMax-M3 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-M3 or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 1M.

### How many benchmarks do MiniMax-M3 and Muse Spark 1.3 share?

28 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Muse Spark 1.3 has 34.