GPT-5.6 Terra (Non-reasoning) — benchmark results
Provider: OpenAI. Released 2026-07-09. Access: API.
Unified ELO 1767 ± 22, rank #179 of 1744 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) - JavaScript | 70 | Accuracy (%) | 91.7 |
| UGI - Natural Intelligence | 52.63 | NatInt Score | 91.5 |
| AA Omniscience - Software Engineering (SWE) - Python | 64 | Accuracy (%) | 91.1 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 58 | Accuracy (%) | 91 |
| AA Omniscience - Software Engineering (SWE) - R | 52 | Accuracy (%) | 91 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 66.67 | Accuracy (%) | 90.9 |
| AA Omniscience - Software Engineering (SWE) - HTML | 68 | Accuracy (%) | 90.8 |
| AA Omniscience - Software Engineering (SWE) - Go | 58 | Accuracy (%) | 90 |
| AA Omniscience - Software Engineering (SWE) | 60.1 | Accuracy (%) | 89.3 |
| AA Omniscience - Software Engineering (SWE) - Julia | 44 | Accuracy (%) | 88.7 |
| AA Omniscience - Software Engineering (SWE) - C | 71 | Accuracy (%) | 88.4 |
| UGI - Writing | 48.2 | Writing Score | 88.1 |
Interactive version: aibenchmarks.dev/model?slug=gpt-5-6-terra-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-10.