# Muse Spark vs Phi-2

> Muse Spark has enough public results to be ranked (#41); Phi-2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/muse-spark-vs-phi-2
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both.
- Phi-2 has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark | Phi-2 |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 50.3 | — |
| Rank | 41 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Muse Spark: 45.6 (#65)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| SciCode | 51.5% | — |
| LMArena Coding | 1482 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |

## Reasoning

- Muse Spark: 34.9 (#61)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 152.09 | 107.62 |
| CritPt | 11.3% | — |
| LMArena Hard Prompts | 1475 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |

## Math

- Muse Spark: 46.8 (#57)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| LMArena Math | 1455 | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Muse Spark: 65.7 (#12)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| GPQA Diamond | 89.8% | — |
| Humanity's Last Exam | 40.6% | — |
| LMArena Expert | 1458 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |

## Multimodal

- Muse Spark: 42.7 (#23)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |

## Multilingual

- Muse Spark: 56.3 (#23)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| LMArena Non-English | 1464 | — |
| LMArena Chinese | 1507 | — |
| LMArena French | 1497 | — |
| LMArena German | 1497 | — |
| LMArena Korean | 1457 | — |
| LMArena Russian | 1467 | — |
| LMArena Spanish | 1471 | — |

## Instruction Following

- Muse Spark: 76.1 (#47)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1443 | — |

## Long Context

- Muse Spark: 44.4 (#65)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1451 | — |

## Writing & Preference

- Muse Spark: 66.2 (#37)
- Phi-2: —

| Benchmark | Muse Spark | Phi-2 |
|---|---|---|
| LMArena Text | 1474 | — |
| LMArena Creative Writing | 1460 | — |
| LMArena Multi-Turn | 1477 | — |

## FAQ

### Is Muse Spark better than Phi-2?

Muse Spark has enough public results to be ranked (#41); Phi-2 does not yet, so treat this comparison as directional.

### How many benchmarks do Muse Spark and Phi-2 share?

1 benchmark has published results for both models. Muse Spark has 27 scored results on Noometry and Phi-2 has 11.