specs at a glance
| Leaderboard rank | #20 of 21 |
|---|---|
| SWE-bench Verified | 75.2% |
| SWE-bench Pro | — |
| Terminal-Bench | — |
| Input price / 1M | $2.50 |
| Output price / 1M | $15 |
| Context window | 1M |
| Open weights | No |
| Access | API · OpenAI platform |
| Maker | OpenAI |
how good is GPT-5.6 Terra at coding?
GPT-5.6 Terra sits at #20 of 21 ranked models, posting 75.2% on SWE-bench Verified — 21.8 points behind #1 Claude Opus 5.
Score provenance: Independent (vals.ai, Jul 22 2026, mini-swe-agent bash-only harness): SWE-bench Verified 75.2% ±1.93, 32nd of 75 systems. Added Jul 27, 2026 from a routine sweep. The middle tier of OpenAI's GPT-5.6 line and by far the weakest of the three on this benchmark: Sol scores 96.2% and Luna 93.0%, both above it, and Luna is cheaper at $1 per 1M. On coding specifically the tier ordering does not follow the price ordering, which is worth knowing before defaulting to the mid tier. Priced $2.50/$15 per 1M, cached input $0.25. Context ~1.05M, max output 128k. Released Jul 9, 2026.
what does GPT-5.6 Terra cost?
$2.50 per 1M input tokens and $15 per 1M output — #14 cheapest of the 20 models we track. Coding workloads are output-heavy, so weight the output rate when budgeting. Run your own volume through the AI API cost calculator for a monthly estimate.
where can you use it?
Available via API · OpenAI platform. As a proprietary model, you're on the maker's infrastructure and release schedule.
More coverageAI coding models on GENZ TECH
Ranked on our AI Coding Leaderboard — scores confirmed against primary sources only, updated 2026-07-27.