GPT-6.1 Terra vs GPT-6 Astra
GPT-6 Astra leads GPT-6.1 Terra by 1.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Terra wins 2 and GPT-6 Astra wins 9 of 12 shared benchmarks. GPT-6.1 Terra is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | GPT-6.1 Terra | GPT-6 Astra |
|---|---|---|
| Agentic coding | 79 | 80 |
| Long-horizon autonomy | 74 | 80 |
| Knowledge-work agents | 56 | 56 |
| Computer use | 63 | 67 |
| Security & context learning | 62 | 63 |
Shared benchmarks
| Benchmark | GPT-6.1 Terra | GPT-6 Astra |
|---|---|---|
| APEX-Agentsindex | 68.3% | 64.7% |
| Vending-Bench 2index | $9,107 | $15,515 |
| CritPt | 28.0% | 31.7% |
| FrontierMath Tier 4 | 92.7% | 97.6% |
| FrontierMath Tiers 1-3 | 90.9% | 93.7% |
| GPQA Diamond | 94.3% | 95.8% |
| MirrorCode | 76.7% | 60.0% |
| OTIS Mock AIME | 100.0% | 100.0% |
| SciCode | 55.1% | 56.5% |
| SimpleBench | 72.2% | 86.5% |
| SimpleQA Verified | 57.3% | 75.6% |
| WeirdML v3 | 28.1% | 42.2% |
Specs and price
| GPT-6.1 Terra | GPT-6 Astra | |
|---|---|---|
| Agent Index | 69 (#8) | 70.9 (#4) |
| Agent $/M | $0.42 | $4.62 |
| Input / output $/M | $1.00 / $5.00 | $10.00 / $50.00 |
| Context | 1.1M | 1.1M |
| Released | Oct 26, 2026 | Sep 4, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 6 |
Don’t pick one. Route.
Shogo can run GPT-6.1 Terra and GPT-6 Astra side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo