GPT-6.1 Terra vs GPT-6 Sol
GPT-6.1 Terra leads GPT-6 Sol by 5.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6.1 Terra wins 5 and GPT-6 Sol wins 5 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 Sol |
|---|---|---|
| Agentic coding | 79 | 72 |
| Long-horizon autonomy | 74 | 76 |
| Knowledge-work agents | 56 | 48 |
| Computer use | 63 | 54 |
| Security & context learning | 62 | 59 |
Shared benchmarks
| Benchmark | GPT-6.1 Terra | GPT-6 Sol |
|---|---|---|
| APEX-Agentsindex | 68.3% | 54.3% |
| Vending-Bench 2index | $9,107 | $14,428 |
| CritPt | 28.0% | 30.9% |
| FrontierMath Tier 4 | 92.7% | 90.0% |
| FrontierMath Tiers 1-3 | 90.9% | 89.8% |
| GPQA Diamond | 94.3% | 94.3% |
| MirrorCode | 76.7% | 48.9% |
| OTIS Mock AIME | 100.0% | 100.0% |
| SciCode | 55.1% | 57.6% |
| SimpleBench | 72.2% | 73.1% |
| SimpleQA Verified | 57.3% | 60.7% |
| WeirdML v3 | 28.1% | 19.7% |
Specs and price
| GPT-6.1 Terra | GPT-6 Sol | |
|---|---|---|
| Agent Index | 69 (#8) | 63.6 (#13) |
| Agent $/M | $0.42 | $0.92 |
| Input / output $/M | $1.00 / $5.00 | $2.00 / $10.00 |
| Context | 1.1M | 1.1M |
| Released | Oct 26, 2026 | Sep 22, 2026 |
| Weights | Closed | Closed |
| API hosts | 4 | 5 |
Don’t pick one. Route.
Shogo can run GPT-6.1 Terra and GPT-6 Sol side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo