# GPT-5.4 nano vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.6 to 41.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-nano-vs-muse-spark
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GPT-5.4 nano scores higher in 0 categories and Muse Spark in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 41.9.
- The biggest single-benchmark swing is ProofBench: 5% for GPT-5.4 nano and 17% for Muse Spark.

## Snapshot

| | GPT-5.4 nano | Muse Spark |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 41.9 | 50.6 |
| Rank | 125 | 46 |
| Context | 400K | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.25 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 nano: 43.6 (#84)
- Muse Spark: 46.2 (#69)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| SciCode | 46.9% | 51.5% |
| LMArena Coding | 1405 | 1481 |
| WeirdML | 49.2% | — |
| ALE-Bench | 1,005 | — |

## Reasoning

- GPT-5.4 nano: 23.7 (#173)
- Muse Spark: 35.9 (#67)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| CritPt | 9.3% | 11.3% |
| LMArena Hard Prompts | 1381 | 1474 |
| Epoch Capabilities Index | 145.81 | 152.04 |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| Chess Puzzles | 30% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| ForecastBench | 57.3 | — |

## Math

- GPT-5.4 nano: 40.9 (#88)
- Muse Spark: 47.8 (#66)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 88.9% |
| ProofBench | 5% | 17% |
| LMArena Math | 1406 | 1455 |
| FrontierMath (Feb 2025 set) | 25.9% | 39% |
| FrontierMath Tier 4 (v1) | 6.3% | 14.6% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |

## Knowledge

- GPT-5.4 nano: 41.9 (#103)
- Muse Spark: 65.7 (#13)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| GPQA Diamond | 78.5% | 89.8% |
| LMArena Expert | 1396 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |

## Multimodal

- GPT-5.4 nano: 36.7 (#78)
- Muse Spark: 43.4 (#24)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| LMArena Vision | 1196 | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- GPT-5.4 nano: 48.6 (#140)
- Muse Spark: 56.1 (#24)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| LMArena Non-English | 1359 | 1464 |
| LMArena Chinese | 1392 | 1509 |
| LMArena French | 1396 | 1497 |
| LMArena German | 1367 | 1497 |
| LMArena Korean | 1320 | 1459 |
| LMArena Russian | 1363 | 1466 |
| LMArena Spanish | 1371 | 1472 |
| LMArena Japanese | 1343 | — |

## Instruction Following

- GPT-5.4 nano: 71.9 (#144)
- Muse Spark: 75.9 (#51)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1362 | 1442 |

## Long Context

- GPT-5.4 nano: 41.6 (#137)
- Muse Spark: 44.4 (#69)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1366 | 1451 |

## Writing & Preference

- GPT-5.4 nano: 55.7 (#142)
- Muse Spark: 66.0 (#39)

| Benchmark | GPT-5.4 nano | Muse Spark |
|---|---|---|
| LMArena Text | 1372 | 1474 |
| LMArena Creative Writing | 1314 | 1459 |
| LMArena Multi-Turn | 1382 | 1477 |

## FAQ

### Is GPT-5.4 nano better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 41.9 on the Noometry Index.

### Is GPT-5.4 nano or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 43.6 in the Noometry coding category.

### How many benchmarks do GPT-5.4 nano and Muse Spark share?

25 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and Muse Spark has 27.