# MiniMax-M2.5 vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 38.3 on the Noometry Index. MiniMax-M2.5 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-m2-5-vs-muse-spark-1-2
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. MiniMax-M2.5 scores higher in 1 category and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 17.5.
- The biggest single-benchmark swing is NYT Connections (extended): 16.8% for MiniMax-M2.5 and 79.2% for Muse Spark 1.2.
- MiniMax-M2.5 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-M2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| Provider | MiniMax | Meta |
| Noometry Index | 38.3 | 50.3 |
| Rank | 188 | 48 |
| Context | 205K | 1.05M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $1.20 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- MiniMax-M2.5: 48.1 (#58)
- Muse Spark 1.2: 49.2 (#51)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1387 | 1533 |
| LMArena Coding | 1381 | 1495 |
| DeepSWE | — | 54.9% |
| SWE-bench Verified (bash only) | 75.8% | — |
| SWE-bench Multilingual | 68.3% | — |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| WeirdML | — | 60.3% |
| ALE-Bench | 618.17 | — |

## Agentic & Tool Use

- MiniMax-M2.5: 30.4 (#77)
- Muse Spark 1.2: 29.4 (#87)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |
| Vending-Bench 2 | -23.16 | — |

## Reasoning

- MiniMax-M2.5: 17.5 (#292)
- Muse Spark 1.2: 51.3 (#34)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 16.8% | 79.2% |
| LMArena Hard Prompts | 1372 | 1486 |
| Epoch Capabilities Index | 146.68 | 154.87 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 55.2% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | — | 17.7% |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |

## Math

- MiniMax-M2.5: 26.9 (#253)
- Muse Spark 1.2: 46.4 (#70)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 4% | 43% |
| LMArena Math | 1378 | 1471 |

## Knowledge

- MiniMax-M2.5: 39.2 (#135)
- Muse Spark 1.2: 54.1 (#53)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1379 | 1480 |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 9.1% | — |

## Multimodal

- MiniMax-M2.5: —
- Muse Spark 1.2: 43.4 (#25)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |

## Multilingual

- MiniMax-M2.5: 47.1 (#152)
- Muse Spark 1.2: 57.1 (#11)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1338 | 1478 |
| LMArena Chinese | 1393 | 1511 |
| LMArena French | 1362 | 1513 |
| LMArena Russian | 1358 | 1487 |
| LMArena Spanish | 1354 | 1498 |
| LMArena German | 1362 | — |
| LMArena Japanese | 1171 | — |
| LMArena Korean | 1232 | — |

## Instruction Following

- MiniMax-M2.5: 71.5 (#148)
- Muse Spark 1.2: 76.7 (#36)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1353 | 1461 |

## Long Context

- MiniMax-M2.5: 37.5 (#216)
- Muse Spark 1.2: 45.2 (#48)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1366 | 1475 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |

## Writing & Preference

- MiniMax-M2.5: 53.9 (#153)
- Muse Spark 1.2: 72.3 (#14)

| Benchmark | MiniMax-M2.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1359 | 1482 |
| LMArena Creative Writing | 1331 | 1449 |
| EQ-Bench Creative Writing | 1361 | 1840 |
| LMArena Multi-Turn | 1364 | 1494 |

## FAQ

### Is MiniMax-M2.5 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 38.3 on the Noometry Index. MiniMax-M2.5 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-M2.5 or Muse Spark 1.2?

MiniMax-M2.5 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-M2.5 or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 48.1 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-M2.5 and Muse Spark 1.2 share?

19 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Muse Spark 1.2 has 31.