# GPT-5.4 mini vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.6 to 45.0 on the Noometry Index.

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

## Summary

- They share 25 benchmarks with published results for both. GPT-5.4 mini scores higher in 0 categories and Muse Spark in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 51.5.

## Snapshot

| | GPT-5.4 mini | Muse Spark |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.0 | 50.6 |
| Rank | 76 | 46 |
| Context | 400K | — |
| Input $/M | $0.75 | — |
| Output $/M | $4.50 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Muse Spark: 46.2 (#69)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| SciCode | 49.9% | 51.5% |
| LMArena Coding | 1438 | 1481 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Muse Spark: —

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Muse Spark: 35.9 (#67)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| CritPt | 10% | 11.3% |
| LMArena Hard Prompts | 1424 | 1474 |
| Epoch Capabilities Index | 148.84 | 152.04 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Muse Spark: 47.8 (#66)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 88.9% |
| ProofBench | 21% | 17% |
| LMArena Math | 1419 | 1455 |
| FrontierMath (Feb 2025 set) | 28.3% | 39% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Muse Spark: 65.7 (#13)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| GPQA Diamond | 86.9% | 89.8% |
| LMArena Expert | 1435 | 1457 |
| Humanity's Last Exam | — | 40.6% |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Muse Spark: 43.4 (#24)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| LMArena Vision | 1245 | 1306 |
| LMArena Document | — | 1444 |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Muse Spark: 56.1 (#24)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| LMArena Non-English | 1405 | 1464 |
| LMArena Chinese | 1446 | 1509 |
| LMArena French | 1440 | 1497 |
| LMArena German | 1409 | 1497 |
| LMArena Korean | 1368 | 1459 |
| LMArena Russian | 1417 | 1466 |
| LMArena Spanish | 1405 | 1472 |
| LMArena Japanese | 1374 | — |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Muse Spark: 75.9 (#51)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1405 | 1442 |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Muse Spark: 44.4 (#69)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1407 | 1451 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Muse Spark: 66.0 (#39)

| Benchmark | GPT-5.4 mini | Muse Spark |
|---|---|---|
| LMArena Text | 1412 | 1474 |
| LMArena Creative Writing | 1370 | 1459 |
| LMArena Multi-Turn | 1429 | 1477 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

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

Muse Spark is the stronger model overall, scoring 50.6 to 45.0 on the Noometry Index.

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

They score almost the same on coding (45.2 vs 46.2); test both on your own repository before choosing.

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

25 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Muse Spark has 27.