GPT-5.4 vs Muse Spark 1.3
Muse Spark 1.3 leads GPT-5.4 by 3.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.4 wins 3 and Muse Spark 1.3 wins 9 of 12 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-5.4 | Muse Spark 1.3 |
|---|---|---|
| Agentic coding | 57 | 60 |
| Long-horizon autonomy | 61 | 64 |
| Knowledge-work agents | 40 | 45 |
| Computer use | 42 | 43 |
| Security & context learning | 54 | 53 |
Shared benchmarks
| Benchmark | GPT-5.4 | Muse Spark 1.3 |
|---|---|---|
| APEX-Agentsindex | 52.4% | 58.6% |
| Chess Puzzles | 48.0% | 37.0% |
| CritPt | 23.4% | 26.0% |
| DTBench | 94.4% | 96.5% |
| FrontierMath Tier 4 | 49.0% | 46.3% |
| FrontierMath Tiers 1-3 | 78.6% | 74.4% |
| LMCA | 52.0% | 53.9% |
| MirrorCode | 23.3% | 54.4% |
| OTIS Mock AIME | 97.8% | 99.2% |
| ProofBench | 56.0% | 58.0% |
| SciCode | 56.6% | 59.7% |
| WebDev Arena | 1463 | 1652 |
Specs and price
| GPT-5.4 | Muse Spark 1.3 | |
|---|---|---|
| Agent Index | 51.6 (#33) | 54.7 (#28) |
| Agent $/M | $1.27 | $0.030 |
| Input / output $/M | $2.50 / $15.00 | $0.10 / $0.20 |
| Context | 1.1M | 1M |
| Released | Mar 5, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 2 |
Don’t pick one. Route.
Shogo can run GPT-5.4 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