# Muse Spark 1.2 vs Nemotron 3 Super

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 40.1 on the Noometry Index. Nemotron 3 Super costs 12× 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/muse-spark-1-2-vs-nemotron-3-super
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Muse Spark 1.2 scores higher in 8 categories and Nemotron 3 Super in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 18.7.
- The biggest single-benchmark swing is NYT Connections (extended): 79.2% for Muse Spark 1.2 and 15.4% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 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 262K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 50.3 | 40.1 |
| Rank | 48 | 153 |
| Context | 1.05M | 262K |
| Input $/M | $1.25 | $0.08 |
| Output $/M | $4.25 | $0.45 |
| Weights | Proprietary | Open |

## Coding

- Muse Spark 1.2: 49.2 (#51)
- Nemotron 3 Super: 39.4 (#158)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| SciCode | 56.4% | 36% |
| WeirdML | 60.3% | 38% |
| LMArena Coding | 1495 | 1403 |
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1533 | — |
| FrontierSWE | 12% | — |
| ALE-Bench | — | 213.9 |

## Agentic & Tool Use

- Muse Spark 1.2: 29.4 (#87)
- Nemotron 3 Super: —

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |

## Reasoning

- Muse Spark 1.2: 51.3 (#34)
- Nemotron 3 Super: 18.7 (#276)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | 79.2% | 15.4% |
| CritPt | 17.7% | 3.1% |
| LMArena Hard Prompts | 1486 | 1386 |
| SimpleBench | 74.5% | — |
| DTBench | 94.7% | — |
| LMCA | 48.4% | — |
| Epoch Capabilities Index | 154.87 | — |

## Math

- Muse Spark 1.2: 46.4 (#70)
- Nemotron 3 Super: 39.6 (#101)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1471 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| ProofBench | 43% | — |

## Knowledge

- Muse Spark 1.2: 54.1 (#53)
- Nemotron 3 Super: 38.9 (#139)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1480 | 1398 |
| SimpleQA Verified | 60.3% | — |

## Multimodal

- Muse Spark 1.2: 43.4 (#25)
- Nemotron 3 Super: —

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1305 | — |

## Multilingual

- Muse Spark 1.2: 57.1 (#11)
- Nemotron 3 Super: 48.4 (#144)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1478 | 1355 |
| LMArena Chinese | 1511 | 1432 |
| LMArena French | 1513 | 1405 |
| LMArena Russian | 1487 | 1336 |
| LMArena Spanish | 1498 | 1417 |
| LMArena German | — | 1341 |

## Instruction Following

- Muse Spark 1.2: 76.7 (#36)
- Nemotron 3 Super: 71.2 (#154)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1461 | 1347 |

## Long Context

- Muse Spark 1.2: 45.2 (#48)
- Nemotron 3 Super: 41.5 (#139)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1475 | 1362 |

## Writing & Preference

- Muse Spark 1.2: 72.3 (#14)
- Nemotron 3 Super: 55.9 (#140)

| Benchmark | Muse Spark 1.2 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1482 | 1378 |
| LMArena Creative Writing | 1449 | 1317 |
| LMArena Multi-Turn | 1494 | 1369 |
| EQ-Bench Creative Writing | 1840 | — |

## FAQ

### Is Muse Spark 1.2 better than Nemotron 3 Super?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 40.1 on the Noometry Index. Nemotron 3 Super costs 12× 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, Muse Spark 1.2 or Nemotron 3 Super?

Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is Muse Spark 1.2 or Nemotron 3 Super better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 39.4 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

### How many benchmarks do Muse Spark 1.2 and Nemotron 3 Super share?

18 benchmarks have published results for both models. Muse Spark 1.2 has 31 scored results on Noometry and Nemotron 3 Super has 21.