GPT-6.1 Terra vs Muse Spark 1.3
GPT-6.1 Terra leads Muse Spark 1.3 by 14.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Terra wins 7 and Muse Spark 1.3 wins 2 of 9 shared benchmarks. Muse Spark 1.3 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| Agentic coding | 79 | 60 |
| Long-horizon autonomy | 74 | 64 |
| Knowledge-work agents | 56 | 45 |
| Computer use | 63 | 43 |
| Security & context learning | 62 | 53 |
Shared benchmarks
| Benchmark | GPT-6.1 Terra | Muse Spark 1.3 |
|---|---|---|
| APEX-Agentsindex | 68.3% | 58.6% |
| CritPt | 28.0% | 26.0% |
| FrontierMath Tier 4 | 92.7% | 46.3% |
| FrontierMath Tiers 1-3 | 90.9% | 74.4% |
| MirrorCode | 76.7% | 54.4% |
| OTIS Mock AIME | 100.0% | 99.2% |
| SciCode | 55.1% | 59.7% |
| SimpleBench | 72.2% | 81.8% |
| WeirdML v3 | 28.1% | 6.7% |
Specs and price
| GPT-6.1 Terra | Muse Spark 1.3 | |
|---|---|---|
| Agent Index | 69 (#8) | 54.7 (#28) |
| Agent $/M | $0.42 | $0.030 |
| Input / output $/M | $1.00 / $5.00 | $0.10 / $0.20 |
| Context | 1.1M | 1M |
| Released | Oct 26, 2026 | Sep 2, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 2 |
Don’t pick one. Route.
Shogo can run GPT-6.1 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