Kimi K3 vs Muse Spark 1.3
Kimi K3 leads Muse Spark 1.3 by 0.2 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Kimi K3 wins 4 and Muse Spark 1.3 wins 9 of 15 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Kimi K3 | Muse Spark 1.3 |
|---|---|---|
| Agentic coding | 63 | 60 |
| Long-horizon autonomy | 65 | 64 |
| Knowledge-work agents | 42 | 45 |
| Computer use | 43 | 43 |
| Security & context learning | 53 | 53 |
Shared benchmarks
| Benchmark | Kimi K3 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agentsindex | 47.8% | 58.6% |
| FrontierSWEindex | 25.9% | 25.8% |
| Chess Puzzles | 37.0% | 37.0% |
| CritPt | 23.4% | 26.0% |
| DTBench | 91.2% | 96.5% |
| FrontierMath Tier 4 | 39.0% | 46.3% |
| FrontierMath Tiers 1-3 | 72.2% | 74.4% |
| LMCA | 52.7% | 53.9% |
| MirrorCode | 54.4% | 54.4% |
| OTIS Mock AIME | 97.2% | 99.2% |
| ProofBench | 87.0% | 58.0% |
| SciCode | 59.5% | 59.7% |
| SimpleBench | 60.7% | 81.8% |
| WebDev Arena | 1674 | 1652 |
| WeirdML v3 | 7.5% | 6.7% |
Specs and price
| Kimi K3 | Muse Spark 1.3 | |
|---|---|---|
| Agent Index | 54.9 (#26) | 54.7 (#28) |
| Agent $/M | $1.39 | $0.030 |
| Input / output $/M | $3.00 / $15.00 | $0.10 / $0.20 |
| Context | 1M | 1M |
| Released | Jul 16, 2026 | Sep 2, 2026 |
| Weights | Open | Closed |
| API hosts | 29 | 2 |
Don’t pick one. Route.
Shogo can run Kimi K3 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