Claude Sonnet 4.5 vs Muse Spark
Claude Sonnet 4.5 (Anthropic) and Muse Spark (Meta AI) compared on benchmarks, pricing, context window, and use-case rankings.
- Muse Spark leads on overall intelligence (ECI 154 vs 147).
- Muse Spark ranks higher for coding (79th vs 33th percentile).
| Attribute | Claude Sonnet 4.5 | Muse Spark |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 147 | 154 |
| Coding | 33 | 79 |
| Math | 32 | 66 |
| Reasoning & Knowledge | 30 | 84 |
| Agentic & Tools | 38 | 64 |
| Specifications | ||
| Developer | Anthropic | Meta AI |
| Family | Claude | — |
| Released | Sep 29, 2025 | Apr 8, 2026 |
| Parameters | — | — |
| Availability | API access | API access |
| Context window | 1M | — |
| Price — $/M input | $3.00 | — |
| Price — $/M output | $15.00 | — |
| Inputs | text, image, file | — |
| Outputs | text | — |
| Benchmarks | ||
| AIME 2024/2025 | 78% | 89% |
| ARC-AGI | 64% | — |
| ARC-AGI-2 | 14% | — |
| FrontierMath | 15% | 39% |
| FrontierMath Tier 4 | 4% | 15% |
| GDPval (win/tie rate) | 50% | — |
| GPQA Diamond | 82% | 90% |
| GSO (code optimization) | 15% | — |
| Humanity's Last Exam | 14% | 41% |
| MATH Level 5 | 98% | — |
| METR task horizon | 2.0 h | — |
| SimpleBench | 54% | — |
| SimpleQA Verified | 24% | 66% |
| SWE-bench Verified | 71% | — |
| Terminal-Bench | 47% | — |
| WebDev Arena | 1391 | 1513 |
| WeirdML | 48% | — |
| SciCode | — | 52% |
| τ²-bench | — | 92% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is Claude Sonnet 4.5 better than Muse Spark?
On Epoch AI's Capabilities Index, Muse Spark scores higher (154) than Claude Sonnet 4.5 (147). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is better for coding, Claude Sonnet 4.5 or Muse Spark?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, Muse Spark ranks higher — 79th vs 33th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.