GPT-5.6 Terra vs Muse Spark 1.3
GPT-5.6 Terra leads Muse Spark 1.3 by 4.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.6 Terra wins 7 and Muse Spark 1.3 wins 7 of 14 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-5.6 Terra | Muse Spark 1.3 |
|---|---|---|
| Agentic coding | 66 | 60 |
| Long-horizon autonomy | 69 | 64 |
| Knowledge-work agents | 47 | 45 |
| Computer use | 48 | 43 |
| Security & context learning | 56 | 53 |
Shared benchmarks
| Benchmark | GPT-5.6 Terra | Muse Spark 1.3 |
|---|---|---|
| APEX-Agentsindex | 58.2% | 58.6% |
| CursorBenchindex | 41.3% | 41.6% |
| Chess Puzzles | 47.0% | 37.0% |
| CritPt | 30.0% | 26.0% |
| DTBench | 93.3% | 96.5% |
| FrontierMath Tier 4 | 70.7% | 46.3% |
| FrontierMath Tiers 1-3 | 86.0% | 74.4% |
| LMCA | 54.9% | 53.9% |
| MirrorCode | 41.1% | 54.4% |
| OTIS Mock AIME | 99.7% | 99.2% |
| ProofBench | 74.0% | 58.0% |
| SciCode | 55.0% | 59.7% |
| SimpleBench | 48.9% | 81.8% |
| WebDev Arena | 1521 | 1652 |
Specs and price
| GPT-5.6 Terra | Muse Spark 1.3 | |
|---|---|---|
| Agent Index | 58.8 (#16) | 54.7 (#28) |
| Agent $/M | $1.02 | $0.030 |
| Input / output $/M | $2.00 / $12.00 | $0.10 / $0.20 |
| Context | 1.1M | 1M |
| Released | Jul 9, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 2 |
Don’t pick one. Route.
Shogo can run GPT-5.6 Terra 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