# Muse Spark 1.2 vs Qwen2-72B

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/muse-spark-1-2-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Muse Spark 1.2 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark 1.2 leads 54.1 to 21.2.
- The biggest single-benchmark swing is WeirdML: 60.3% for Muse Spark 1.2 and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.3 | 30.0 |
| Rank | 48 | 300 |
| Context | 1.05M | — |
| Input $/M | $1.25 | — |
| Output $/M | $4.25 | — |
| Weights | Proprietary | Open |

## Coding

- Muse Spark 1.2: 49.2 (#51)
- Qwen2-72B: 29.1 (#310)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| WeirdML | 60.3% | 11.3% |
| LMArena Coding | 1495 | 1196 |
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1533 | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Muse Spark 1.2: 29.4 (#87)
- Qwen2-72B: 17.0 (#146)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| APEX-Agents | 36.4% | — |
| TheAgentCompany | — | 1.1% |
| GDP.pdf | 16% | — |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Muse Spark 1.2: 51.3 (#34)
- Qwen2-72B: 23.2 (#181)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1486 | 1191 |
| Epoch Capabilities Index | 154.87 | 125.28 |
| SimpleBench | 74.5% | — |
| NYT Connections (extended) | 79.2% | — |
| CritPt | 17.7% | — |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |

## Math

- Muse Spark 1.2: 46.4 (#70)
- Qwen2-72B: 30.2 (#236)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1471 | 1235 |
| ProofBench | 43% | — |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Muse Spark 1.2: 54.1 (#53)
- Qwen2-72B: 21.2 (#275)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1480 | 1171 |
| GPQA Diamond | — | 40.8% |
| SimpleQA Verified | 60.3% | — |
| MMLU | — | 82.4% |

## Multimodal

- Muse Spark 1.2: 43.4 (#25)
- Qwen2-72B: —

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1305 | — |

## Multilingual

- Muse Spark 1.2: 57.1 (#11)
- Qwen2-72B: 35.9 (#244)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1478 | 1176 |
| LMArena Chinese | 1511 | 1240 |
| LMArena French | 1513 | 1170 |
| LMArena Russian | 1487 | 1169 |
| LMArena Spanish | 1498 | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |

## Instruction Following

- Muse Spark 1.2: 76.7 (#36)
- Qwen2-72B: 61.7 (#241)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1461 | 1181 |

## Long Context

- Muse Spark 1.2: 45.2 (#48)
- Qwen2-72B: 36.1 (#235)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1475 | 1192 |

## Writing & Preference

- Muse Spark 1.2: 72.3 (#14)
- Qwen2-72B: 40.8 (#241)

| Benchmark | Muse Spark 1.2 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1482 | 1203 |
| LMArena Creative Writing | 1449 | 1181 |
| LMArena Multi-Turn | 1494 | 1196 |
| EQ-Bench Creative Writing | 1840 | — |

## FAQ

### Is Muse Spark 1.2 better than Qwen2-72B?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.0 on the Noometry Index.

### Is Muse Spark 1.2 or Qwen2-72B better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 29.1 in the Noometry coding category.

### How many benchmarks do Muse Spark 1.2 and Qwen2-72B share?

16 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Qwen2-72B has 26.