Model comparison
Claude Sonnet 5 vs Muse Spark 1.2
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 49.8 on the Noometry Index. Muse Spark 1.2 costs 2.0× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
MetaSummary
- They share 26 benchmarks with published results for both. Claude Sonnet 5 scores higher in 4 categories and Muse Spark 1.2 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.1 to 43.8.
- The biggest single-benchmark swing is ProofBench: 77% for Claude Sonnet 5 and 43% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5 | Muse Spark 1.2 | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 54.5 | 49.8 |
| Released | 2026-06-29 | 2026-08-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 131K |
| Input $ / M tokens | $2 | $1.25 |
| Output $ / M tokens | $10 | $4.25 |
| Results tracked | 51 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#20), Muse Spark 1.2: 48.6 (#49)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| DeepSWE | 53.8% | 54.9% |
| LMArena WebDev | 1540 | 1532 |
| SciCode | 53.6% | 56.4% |
| WeirdML | 68.8% | 60.3% |
| LMArena Coding | 1483 | 1497 |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| FrontierSWE | — | 12% |
| GSO | 37.3% | — |
| ALE-Bench | 1,463 | — |
Agentic & Tool Use Claude Sonnet 5 leads
Claude Sonnet 5: 42.7 (#16), Muse Spark 1.2: 29.5 (#77)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | 54.5% | 36.4% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 16% |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Muse Spark 1.2 leads
Claude Sonnet 5: 48.2 (#37), Muse Spark 1.2: 50.4 (#32)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | 60.6% | 74.5% |
| NYT Connections (extended) | 75.1% | 79.2% |
| CritPt | 16.9% | 17.7% |
| LMArena Hard Prompts | 1461 | 1490 |
| DTBench | 92.5% | 94.7% |
| LMCA | 50% | 48.4% |
| Epoch Capabilities Index | 156.34 | 155.18 |
| Chess Puzzles | 35% | — |
| Mystery Game Puzzles | 35% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5 leads
Claude Sonnet 5: 66.1 (#21), Muse Spark 1.2: 43.8 (#68)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 77% | 43% |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| LMArena Math | 1467 | — |
Knowledge Claude Sonnet 5 leads
Claude Sonnet 5: 55.7 (#42), Muse Spark 1.2: 53.9 (#49)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 33.7% | 60.3% |
| LMArena Expert | 1491 | 1485 |
| GPQA Diamond | 90.5% | — |
Multimodal Too close to call
Claude Sonnet 5: 42.4 (#26), Muse Spark 1.2: 42.6 (#24)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1275 | 1304 |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Muse Spark 1.2 leads
Claude Sonnet 5: 54.0 (#55), Muse Spark 1.2: 57.4 (#10)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1431 | 1479 |
| LMArena Chinese | 1475 | 1519 |
| LMArena Russian | 1452 | 1494 |
| LMArena French | 1457 | — |
| LMArena German | 1448 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Too close to call
Claude Sonnet 5: 76.6 (#39), Muse Spark 1.2: 77.1 (#30)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1453 | 1466 |
Long Context Too close to call
Claude Sonnet 5: 44.8 (#53), Muse Spark 1.2: 45.4 (#35)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1464 | 1483 |
Writing & Preference Muse Spark 1.2 leads
Claude Sonnet 5: 69.4 (#24), Muse Spark 1.2: 72.6 (#14)
| Benchmark | Claude Sonnet 5 | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1443 | 1486 |
| LMArena Creative Writing | 1416 | 1444 |
| EQ-Bench Creative Writing | 1794 | 1840 |
| LMArena Multi-Turn | 1454 | 1504 |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Muse Spark 1.2?
Claude Sonnet 5 is the stronger model overall, scoring 54.5 to 49.8 on the Noometry Index. Muse Spark 1.2 costs 2.0× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 5 or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Muse Spark 1.2 better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 5 and Muse Spark 1.2 share?
26 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Muse Spark 1.2 has 28.