Model comparison
Claude Sonnet 4.5 vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 44.1 on the Noometry Index.
Last verified . 32 shared benchmarks.
MetaSummary
- They share 32 benchmarks with published results for both. Claude Sonnet 4.5 scores higher in 1 category and Muse Spark 1.3 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 32.3.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 23.9% for Claude Sonnet 4.5 and 74.4% for Muse Spark 1.3.
- Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.5.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4.5 | Muse Spark 1.3 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 44.1 | 54.8 |
| Released | 2025-09-29 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 131K |
| Input $ / M tokens | $3 | $1.25 |
| Output $ / M tokens | $15 | $4.25 |
| Results tracked | 73 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Claude Sonnet 4.5: 47.3 (#61), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1393 | 1657 |
| SciCode | 44.7% | 59.7% |
| LMArena Coding | 1489 | 1514 |
| SWE-bench Verified | 71.3% | — |
| SWE-bench Verified (bash only) | 71.4% | — |
| CursorBench | — | 41.6% |
| SWE-bench Multilingual | 67% | — |
| GSO | 14.7% | — |
| WeirdML | 47.7% | — |
| ALE-Bench | 796.15 | — |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Too close to call
Claude Sonnet 4.5: 38.3 (#32), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| Terminal-Bench | 46.5% | — |
| APEX-Agents | — | 57.8% |
| 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% | — |
| GDP.pdf | — | 27.6% |
| LMArena Search | 1159 | — |
| METR Time Horizons | 67.4% | — |
| Vending-Bench 2 | 3,839 | — |
Reasoning Muse Spark 1.3 leads
Claude Sonnet 4.5: 26.9 (#125), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 37.3% | 85.1% |
| CritPt | 1.1% | 26% |
| Chess Puzzles | 12% | 38% |
| LMArena Hard Prompts | 1462 | 1503 |
| Mystery Game Puzzles | 17% | 25% |
| DTBench | 83.2% | 96.5% |
| LMCA | 38.8% | 53.9% |
| Epoch Capabilities Index | 146.84 | 156.75 |
| ARC-AGI-2 | 13.6% | — |
| SimpleBench | 54.3% | — |
| Kagi LLM Benchmark | 57.9% | — |
| ARC-AGI-1 | 63.7% | — |
| EnigmaEval | 6% | — |
| EBR-Bench | 2.4% | — |
| Bench to the Future 3 | — | 0.14 |
| ForecastBench | 61.9 | — |
Math Muse Spark 1.3 leads
Claude Sonnet 4.5: 32.3 (#216), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 23.9% | 74.4% |
| FrontierMath Tier 4 | 2.4% | 46.3% |
| OTIS Mock AIME 2024-2025 | 77.8% | 99.2% |
| ProofBench | 19% | 58% |
| LMArena Math | 1449 | 1494 |
| Omni-MATH | 55.3% | — |
| MATH Level 5 | 97.7% | — |
| FrontierMath (Feb 2025 set) | 15.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 4.5 leads
Claude Sonnet 4.5: 48.4 (#76), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1482 | 1516 |
| GPQA Diamond | 82.3% | — |
| Humanity's Last Exam | 13.7% | — |
| SimpleQA Verified | 30.7% | — |
| MMLU-Pro | 86.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 68.6% | — |
Multimodal Muse Spark 1.3 leads
Claude Sonnet 4.5: 34.8 (#89), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Document | 1450 | 1471 |
| LMArena Vision | — | 1309 |
| VPCT | 39.8% | — |
Multilingual Muse Spark 1.3 leads
Claude Sonnet 4.5: 53.4 (#69), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1425 | 1481 |
| LMArena Chinese | 1459 | 1529 |
| LMArena French | 1458 | 1524 |
| LMArena German | 1427 | 1515 |
| LMArena Japanese | 1390 | 1474 |
| LMArena Korean | 1403 | 1501 |
| LMArena Russian | 1437 | 1490 |
| LMArena Spanish | 1457 | 1490 |
Instruction Following Muse Spark 1.3 leads
Claude Sonnet 4.5: 75.0 (#78), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1459 | 1477 |
| IFEval | 85% | — |
Long Context Too close to call
Claude Sonnet 4.5: 45.2 (#46), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1476 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Claude Sonnet 4.5: 66.5 (#34), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Claude Sonnet 4.5 | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1439 | 1490 |
| LMArena Creative Writing | 1442 | 1455 |
| EQ-Bench Creative Writing | 1678 | 1906 |
| LMArena Multi-Turn | 1465 | 1482 |
| WildBench | 85.4% | — |
Frequently asked questions
Is Claude Sonnet 4.5 better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 44.1 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.5 or Muse Spark 1.3?
Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Claude Sonnet 4.5 lists at $3 and $15.
Is Claude Sonnet 4.5 or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 47.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4.5 and Muse Spark 1.3 share?
32 benchmarks have published results for both models. Claude Sonnet 4.5 has 73 scored results on Noometry and Muse Spark 1.3 has 37.