GPT-6 Astra (2026-09-03): benchmark results
Provider: OpenAI. Released 2026-09-03. Access: API.
Aggregate Rating 1890 ± 50, rank #23 of 10916 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| 3DVerifier - Explanation-aware Overall | 65.8 | Explanation-aware balanced accuracy (%) | 100 |
| 3DVerifier - Material | 71.5 | Balanced accuracy (%) | 100 |
| 3DVerifier - Motion Binary | 57.5 | Balanced accuracy (%) | 100 |
| 3DVerifier - Motion Four-class | 54.5 | Four-class accuracy (%) | 100 |
| 3DVerifier - Overall | 69.4 | Balanced accuracy (%) | 100 |
| 3DVerifier - Part | 72.1 | Balanced accuracy (%) | 100 |
| 3DVerifier - Part Grounding | 89.6 | Balanced accuracy (%) | 100 |
| 3DVerifier - Part Relation | 90.3 | Balanced accuracy (%) | 100 |
| LLM Chess (Saplin) | 1613.84 | Native anchored-opponent Elo (signed points) | 100 |
| 3DVerifier - Affordance Region | 76.3 | Balanced accuracy (%) | 88.9 |
| 3DVerifier - Object | 75.3 | Balanced accuracy (%) | 77.8 |
| 3DVerifier - Identity | 55.5 | Balanced accuracy (%) | 66.7 |
Interactive version: theaggregate.ai/model?slug=gpt-6-astra-2026-09-03 · How It Works · Data refreshed daily, snapshot 2026-11-08.