# Claude Sonnet 4.5 vs Muse Spark

> Muse Spark is the stronger model overall, scoring 50.3 to 44.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-5-vs-muse-spark
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 3 categories and Muse Spark in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 48.4.
- The biggest single-benchmark swing is Humanity's Last Exam: 13.7% for Claude Sonnet 4.5 and 40.6% for Muse Spark.

## Snapshot

| | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 44.0 | 50.3 |
| Rank | 76 | 41 |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Sonnet 4.5: 47.8 (#54)
- Muse Spark: 45.6 (#65)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| SciCode | 44.7% | 51.5% |
| LMArena Coding | 1489 | 1482 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| LMArena WebDev | 1393 | — |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |

## Agentic & Tool Use

- Claude Sonnet 4.5: 38.1 (#30)
- Muse Spark: —

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| Berkeley Function Calling Leaderboard | 73.2% | — |
| GDPval | 42.5% | — |
| Remote Labor Index | 2.1% | — |
| τ²-bench Airline | 72% | — |
| τ²-bench Banking | 25.3% | — |
| τ²-bench Retail | 72.4% | — |
| τ²-bench Telecom | 84.9% | — |
| Cybench | 60% | — |
| DeepResearch Bench | 52.6% | — |
| OSWorld | 62.9% | — |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |

## Reasoning

- Claude Sonnet 4.5: 26.9 (#113)
- Muse Spark: 34.9 (#61)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| CritPt | 1.1% | 11.3% |
| LMArena Hard Prompts | 1462 | 1475 |
| Epoch Capabilities Index | 146.84 | 152.09 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| NYT Connections (extended) | 37.3% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | 12% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 83.2% | — |
| LMCA | 38.8% | — |
| ForecastBench | 61.9 | — |

## Math

- Claude Sonnet 4.5: 31.9 (#190)
- Muse Spark: 46.8 (#57)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 88.9% |
| ProofBench | 19% | 17% |
| LMArena Math | 1448 | 1455 |
| FrontierMath (Feb 2025 set) | 15.2% | 39% |
| FrontierMath Tier 4 (v1) | 4.2% | 14.6% |
| FrontierMath (Tiers 1-3) | 23.9% | — |
| FrontierMath Tier 4 | 2.4% | — |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |

## Knowledge

- Claude Sonnet 4.5: 48.4 (#70)
- Muse Spark: 65.7 (#12)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| GPQA Diamond | 82.3% | 89.8% |
| Humanity's Last Exam | 13.7% | 40.6% |
| LMArena Expert | 1483 | 1458 |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |

## Multimodal

- Claude Sonnet 4.5: 34.1 (#84)
- Muse Spark: 42.7 (#23)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| LMArena Document | 1450 | 1444 |
| LMArena Vision | — | 1306 |
| VPCT | 39.8% | — |

## Multilingual

- Claude Sonnet 4.5: 53.6 (#65)
- Muse Spark: 56.3 (#23)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| LMArena Non-English | 1425 | 1464 |
| LMArena Chinese | 1459 | 1507 |
| LMArena French | 1459 | 1497 |
| LMArena German | 1427 | 1497 |
| LMArena Korean | 1403 | 1457 |
| LMArena Russian | 1436 | 1467 |
| LMArena Spanish | 1457 | 1471 |
| LMArena Japanese | 1390 | — |

## Instruction Following

- Claude Sonnet 4.5: 75.2 (#74)
- Muse Spark: 76.1 (#47)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1459 | 1443 |
| IFEval | 85% | — |

## Long Context

- Claude Sonnet 4.5: 45.2 (#45)
- Muse Spark: 44.4 (#65)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1476 | 1451 |

## Writing & Preference

- Claude Sonnet 4.5: 66.7 (#33)
- Muse Spark: 66.2 (#37)

| Benchmark | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| LMArena Text | 1439 | 1474 |
| LMArena Creative Writing | 1442 | 1460 |
| LMArena Multi-Turn | 1465 | 1477 |
| EQ-Bench Creative Writing | 1678 | — |
| WildBench | 85.4% | — |

## FAQ

### Is Claude Sonnet 4.5 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.3 to 44.0 on the Noometry Index.

### Is Claude Sonnet 4.5 or Muse Spark better for coding?

Claude Sonnet 4.5 scores higher on coding benchmarks: 47.8 versus 45.6 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4.5 and Muse Spark share?

26 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Muse Spark has 27.