# Muse Spark 1.2 vs Sonar

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 37.8 on the Noometry Index. Sonar costs 2.0× 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-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 20.3.
- Sonar is cheaper at $1 / $1 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 128K.

## Snapshot

| | Muse Spark 1.2 | Sonar |
|---|---|---|
| Provider | Meta | Perplexity |
| Noometry Index | 49.8 | 37.8 |
| Rank | 44 | 184 |
| Context | 1.05M | 128K |
| Input $/M | $1.25 | $1 |
| Output $/M | $4.25 | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- Muse Spark 1.2: 48.6 (#49)
- Sonar: 35.1 (#217)

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| DeepSWE | 54.9% | — |
| LMArena WebDev | 1532 | — |
| FrontierSWE | 12% | — |
| SciCode | 56.4% | — |
| WeirdML | 60.3% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1497 | — |

## Agentic & Tool Use

- Muse Spark 1.2: 29.5 (#77)
- Sonar: —

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| APEX-Agents | 36.4% | — |
| GDP.pdf | 16% | — |

## Reasoning

- Muse Spark 1.2: 50.4 (#32)
- Sonar: 20.3 (#221)

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| SimpleBench | 74.5% | — |
| NYT Connections (extended) | 79.2% | — |
| CritPt | 17.7% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1490 | — |
| DTBench | 94.7% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 48.4% | — |
| Epoch Capabilities Index | 155.18 | — |
| LiveBench | — | 46.9% |

## Math

- Muse Spark 1.2: 43.8 (#68)
- Sonar: 31.3 (#197)

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| ProofBench | 43% | — |
| LiveBench Math | — | 41.6% |

## Knowledge

- Muse Spark 1.2: 53.9 (#49)
- Sonar: —

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| SimpleQA Verified | 60.3% | — |
| LMArena Expert | 1485 | — |

## Multimodal

- Muse Spark 1.2: 42.6 (#24)
- Sonar: —

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| LMArena Vision | 1304 | — |

## Multilingual

- Muse Spark 1.2: 57.4 (#10)
- Sonar: —

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| LMArena Non-English | 1479 | — |
| LMArena Chinese | 1519 | — |
| LMArena Russian | 1494 | — |

## Instruction Following

- Muse Spark 1.2: 77.1 (#30)
- Sonar: 71.5 (#146)

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1466 | — |

## Long Context

- Muse Spark 1.2: 45.4 (#35)
- Sonar: —

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| LMArena Longer Query | 1483 | — |

## Writing & Preference

- Muse Spark 1.2: 72.6 (#14)
- Sonar: 52.6 (#166)

| Benchmark | Muse Spark 1.2 | Sonar |
|---|---|---|
| LMArena Text | 1486 | — |
| LMArena Creative Writing | 1444 | — |
| EQ-Bench Creative Writing | 1840 | — |
| LMArena Multi-Turn | 1504 | — |
| LiveBench Language | — | 44.1% |

## FAQ

### Is Muse Spark 1.2 better than Sonar?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 37.8 on the Noometry Index. Sonar costs 2.0× 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 Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is Muse Spark 1.2 or Sonar better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 35.1 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 128K.

### How many benchmarks do Muse Spark 1.2 and Sonar share?

0 benchmarks have published results for both models. Muse Spark 1.2 has 28 scored results on Noometry and Sonar has 7.