GPT-5.6 Terra (Medium): benchmark results
GPT-5.6 Terra evaluated at the medium reasoning-effort setting. Provider: OpenAI. Released 2026-07-09. Access: API.
Aggregate Rating 1764 ± 11, rank #208 of 2168 rated models, from 144 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ParseBench - Charts | 67.86 | ChartDataPointMatch Score | 96.4 |
| AA GDP.pdf - Construction - Criterion Pass Rate | 75.79 | Criterion Pass Rate (%) | 93.8 |
| K-Bench - Risk | 94.59 | Risk Score (%, Default v1 prompt) | 91.8 |
| PLCC - History | 94 | Accuracy (%) | 89.8 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 60 | Omniscience Index | 89.5 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 56.5 | Omniscience Index | 89.1 |
| PLCC - Art & Entertainment | 86 | Accuracy (%) | 87.8 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 56 | Omniscience Index | 86.5 |
| AA CritPt | 17.43 | Accuracy (%) | 86.4 |
| AA-Omniscience Index - Software Engineering (SWE) - TypeScript | 53.33 | Omniscience Index | 85.8 |
| LisanBench | 0.21 | Mean Path Length / Current Maximum | 85.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | 28 | Omniscience Index | 85.4 |
Interactive version: theaggregate.ai/model?slug=gpt-5-6-terra-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.