# GPT-4.5 vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-muse-spark-1-2
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Muse Spark 1.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 50.4 to 14.1.
- The biggest single-benchmark swing is SimpleBench: 34.5% for GPT-4.5 and 74.5% for Muse Spark 1.2.

## Snapshot

| | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 36.9 | 49.8 |
| Rank | 200 | 44 |
| Context | — | 1.05M |
| Input $/M | — | $1.25 |
| Output $/M | — | $4.25 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.5: 41.8 (#102)
- Muse Spark 1.2: 48.6 (#49)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| WeirdML | 39.4% | 60.3% |
| LMArena Coding | 1397 | 1497 |
| DeepSWE | — | 54.9% |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1532 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- Muse Spark 1.2: 29.5 (#77)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Cybench | 17.5% | — |
| GDP.pdf | — | 16% |

## Reasoning

- GPT-4.5: 14.1 (#320)
- Muse Spark 1.2: 50.4 (#32)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 34.5% | 74.5% |
| LMArena Hard Prompts | 1404 | 1490 |
| Epoch Capabilities Index | 136.74 | 155.18 |
| ARC-AGI-2 | 0.8% | — |
| NYT Connections (extended) | — | 79.2% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 17.7% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| DTBench | — | 94.7% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 48.4% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 31.0 (#200)
- Muse Spark 1.2: 43.8 (#68)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 43% |
| LiveBench Math | 69.3% | — |
| LMArena Math | 1412 | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.4 (#205)
- Muse Spark 1.2: 53.9 (#49)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1394 | 1485 |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | — | 60.3% |
| Confabulations | 13.6% | — |

## Multimodal

- GPT-4.5: 37.0 (#68)
- Muse Spark 1.2: 42.6 (#24)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1195 | 1304 |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.7 (#78)
- Muse Spark 1.2: 57.4 (#10)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1413 | 1479 |
| LMArena Chinese | 1421 | 1519 |
| LMArena Russian | 1419 | 1494 |
| LMArena French | 1417 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- Muse Spark 1.2: 77.1 (#30)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1466 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#150)
- Muse Spark 1.2: 45.4 (#35)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1406 | 1483 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- Muse Spark 1.2: 72.6 (#14)

| Benchmark | GPT-4.5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1417 | 1486 |
| LMArena Creative Writing | 1394 | 1444 |
| EQ-Bench Creative Writing | 1258 | 1840 |
| LMArena Multi-Turn | 1444 | 1504 |
| Short-Story Creative Writing | 75.6% | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 49.8 to 36.9 on the Noometry Index.

### Is GPT-4.5 or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 48.6 versus 41.8 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and Muse Spark 1.2 share?

16 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Muse Spark 1.2 has 28.