# Muse Spark 1.1 vs Phi-4

> Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.9 on the Noometry Index. Phi-4 costs 23× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/muse-spark-1-1-vs-phi-4
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Muse Spark 1.1 scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Muse Spark 1.1 leads 73.6 to 40.7.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
- Muse Spark 1.1 accepts more context: 1.05M tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.

## Snapshot

| | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 49.9 | 30.9 |
| Rank | 43 | 269 |
| Context | 1.05M | 128K |
| Input $/M | $1.25 | $0.07 |
| Output $/M | $4.25 | $0.14 |
| Weights | Proprietary | Open |

## Coding

- Muse Spark 1.1: 50.8 (#38)
- Phi-4: 33.8 (#237)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Coding | 1497 | 1231 |
| DeepSWE | 53.3% | — |
| LMArena WebDev | 1542 | — |
| SciCode | 58.8% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |

## Agentic & Tool Use

- Muse Spark 1.1: 33.9 (#45)
- Phi-4: 22.6 (#120)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| τ²-bench Banking | 40.5% | — |
| BALROG | — | 11.6% |
| GBAEval | 7.9% | — |
| GDP.pdf | 15% | — |
| Vending-Bench 2 | 6,520 | — |

## Reasoning

- Muse Spark 1.1: 45.9 (#41)
- Phi-4: 17.0 (#287)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1486 | 1220 |
| Epoch Capabilities Index | 154.32 | 130.43 |
| NYT Connections (extended) | 84.9% | — |
| CritPt | 15.1% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| DTBench | 94.4% | — |
| LiveBench Data Analysis | — | 45.2% |
| LMCA | 49.9% | — |
| Surface Evolver Bench | 52.5% | — |
| LiveBench | — | 41.6% |

## Math

- Muse Spark 1.1: 44.0 (#67)
- Phi-4: 19.6 (#279)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Math | 1477 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| ProofBench | 39% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |

## Knowledge

- Muse Spark 1.1: 52.8 (#55)
- Phi-4: 32.5 (#204)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Expert | 1480 | 1203 |
| GPQA Diamond | — | 56.1% |
| SimpleQA Verified | 57.8% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |

## Multimodal

- Muse Spark 1.1: 41.9 (#28)
- Phi-4: —

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Vision | 1292 | — |
| LMArena Document | 1465 | — |

## Multilingual

- Muse Spark 1.1: 56.8 (#16)
- Phi-4: 37.4 (#232)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1471 | 1197 |
| LMArena Chinese | 1518 | 1211 |
| LMArena French | 1494 | 1223 |
| LMArena German | 1466 | 1222 |
| LMArena Japanese | 1445 | 1158 |
| LMArena Korean | 1459 | 1151 |
| LMArena Russian | 1482 | 1209 |
| LMArena Spanish | 1471 | 1234 |

## Instruction Following

- Muse Spark 1.1: 76.8 (#36)
- Phi-4: 60.6 (#246)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1457 | 1201 |
| LiveBench Instruction Following | — | 58.4% |

## Long Context

- Muse Spark 1.1: 44.8 (#55)
- Phi-4: 36.9 (#221)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1463 | 1217 |

## Writing & Preference

- Muse Spark 1.1: 73.6 (#11)
- Phi-4: 40.7 (#239)

| Benchmark | Muse Spark 1.1 | Phi-4 |
|---|---|---|
| LMArena Text | 1479 | 1217 |
| LMArena Creative Writing | 1440 | 1182 |
| LMArena Multi-Turn | 1484 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| EQ-Bench Creative Writing | 1927 | — |
| EQ-Bench 4 | 1260 | — |
| LiveBench Language | — | 25.6% |

## FAQ

### Is Muse Spark 1.1 better than Phi-4?

Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 30.9 on the Noometry Index. Phi-4 costs 23× less per token, which makes it the better buy when Muse Spark 1.1's lead doesn't matter for your workload.

### Which is cheaper, Muse Spark 1.1 or Phi-4?

Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.

### Is Muse Spark 1.1 or Phi-4 better for coding?

Muse Spark 1.1 scores higher on coding benchmarks: 50.8 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.1 does, with 1.05M tokens against 128K.

### How many benchmarks do Muse Spark 1.1 and Phi-4 share?

18 benchmarks have published results for both models. Muse Spark 1.1 has 36 scored results on Noometry and Phi-4 has 37.