# Muse Spark 1.2 vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.5 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 1.9× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/muse-spark-1-2-vs-qwen3-7-max
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Muse Spark 1.2 scores higher in 5 categories and Qwen3.7 Max in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 46.4.
- The biggest single-benchmark swing is ProofBench: 43% for Muse Spark 1.2 and 26% for Qwen3.7 Max.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.3 | 51.5 |
| Rank | 48 | 42 |
| Context | 1.05M | 1M |
| Input $/M | $1.25 | $2.50 |
| Output $/M | $4.25 | $7.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Muse Spark 1.2: 49.2 (#51)
- Qwen3.7 Max: 50.4 (#45)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena WebDev | 1533 | 1515 |
| SciCode | 56.4% | 48.8% |
| LMArena Coding | 1495 | 1498 |
| SWE-bench Verified | — | 77.3% |
| DeepSWE | 54.9% | — |
| FrontierSWE | 12% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Muse Spark 1.2: 29.4 (#87)
- Qwen3.7 Max: 22.1 (#135)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GBAEval | — | 0.4% |
| GDP.pdf | 16% | — |

## Reasoning

- Muse Spark 1.2: 51.3 (#34)
- Qwen3.7 Max: 49.2 (#38)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 74.5% | 70.4% |
| NYT Connections (extended) | 79.2% | 85.1% |
| CritPt | 17.7% | 13.4% |
| LMArena Hard Prompts | 1486 | 1483 |
| DTBench | 94.7% | 92.3% |
| LMCA | 48.4% | 44% |
| Epoch Capabilities Index | 154.87 | 153.68 |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |

## Math

- Muse Spark 1.2: 46.4 (#70)
- Qwen3.7 Max: 62.4 (#32)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| ProofBench | 43% | 26% |
| LMArena Math | 1471 | 1490 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |

## Knowledge

- Muse Spark 1.2: 54.1 (#53)
- Qwen3.7 Max: 61.6 (#28)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| SimpleQA Verified | 60.3% | 55.8% |
| LMArena Expert | 1480 | 1488 |
| GPQA Diamond | — | 90.9% |

## Multimodal

- Muse Spark 1.2: 43.4 (#25)
- Qwen3.7 Max: —

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1305 | — |

## Multilingual

- Muse Spark 1.2: 57.1 (#11)
- Qwen3.7 Max: 56.9 (#15)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1478 | 1474 |
| LMArena Chinese | 1511 | 1530 |
| LMArena Russian | 1487 | 1484 |
| LMArena French | 1513 | — |
| LMArena Spanish | 1498 | — |

## Instruction Following

- Muse Spark 1.2: 76.7 (#36)
- Qwen3.7 Max: 76.7 (#38)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1461 | 1460 |

## Long Context

- Muse Spark 1.2: 45.2 (#48)
- Qwen3.7 Max: 45.4 (#40)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1475 | 1482 |

## Writing & Preference

- Muse Spark 1.2: 72.3 (#14)
- Qwen3.7 Max: 65.0 (#54)

| Benchmark | Muse Spark 1.2 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1482 | 1476 |
| LMArena Creative Writing | 1449 | 1449 |
| LMArena Multi-Turn | 1494 | 1481 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | — | 1110 |

## FAQ

### Is Muse Spark 1.2 better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 50.3 on the Noometry Index. Muse Spark 1.2 costs 1.9× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.

### Which is cheaper, Muse Spark 1.2 or Qwen3.7 Max?

Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.

### Is Muse Spark 1.2 or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 49.2 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 1M.

### How many benchmarks do Muse Spark 1.2 and Qwen3.7 Max share?

22 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Qwen3.7 Max has 33.