Claude Sonnet 5 vs Muse Spark 1.3
Muse Spark 1.3 leads Claude Sonnet 5 by 2.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5 wins 3 and Muse Spark 1.3 wins 12 of 15 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Sonnet 5 | Muse Spark 1.3 |
|---|---|---|
| Agentic coding | 57 | 60 |
| Long-horizon autonomy | 65 | 64 |
| Knowledge-work agents | 43 | 45 |
| Computer use | 40 | 43 |
| Security & context learning | 51 | 53 |
Shared benchmarks
| Benchmark | Claude Sonnet 5 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agentsindex | 54.5% | 58.6% |
| CursorBenchindex | 34.1% | 41.6% |
| Chess Puzzles | 45.0% | 37.0% |
| CritPt | 16.9% | 26.0% |
| DTBench | 92.5% | 96.5% |
| FrontierMath Tier 4 | 29.3% | 46.3% |
| FrontierMath Tiers 1-3 | 65.6% | 74.4% |
| GeoBench | 74.0% | 86.0% |
| LMCA | 50.0% | 53.9% |
| MirrorCode | 63.3% | 54.4% |
| OTIS Mock AIME | 94.7% | 99.2% |
| ProofBench | 77.0% | 58.0% |
| SciCode | 54.3% | 59.7% |
| SimpleBench | 60.6% | 81.8% |
| WebDev Arena | 1537 | 1652 |
Specs and price
| Claude Sonnet 5 | Muse Spark 1.3 | |
|---|---|---|
| Agent Index | 52.4 (#32) | 54.7 (#28) |
| Agent $/M | $0.92 | $0.030 |
| Input / output $/M | $2.00 / $10.00 | $0.10 / $0.20 |
| Context | 1M | 1M |
| Released | Jun 30, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 5 | 2 |
Don’t pick one. Route.
Shogo can run Claude Sonnet 5 and Muse Spark 1.3 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo