GPT-6.2 Astra Pro: benchmark results
Provider: OpenAI. Released 2026-11-17. Access: API.
Aggregate Rating 1990 ± 11, rank #2 of 10489 rated models, from 14 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| DuelLab GameBench 2 - Reasoning Variants | 97.15 | GameBench2 normalized score (0–100) | 99.7 |
| Arabic Broad Leaderboard - Translation (incl Dialects) | 8.19 | Average Score (0-10) | 99.2 |
| Arabic Broad Leaderboard - MMLU | 9.92 | Average Score (0-10) | 98 |
| MineBench | 2134 | Elo Rating | 97.6 |
| Arabic Broad Leaderboard | 9.14 | Average Score (0-10) | 93 |
| Arabic Broad Leaderboard - Trust & Safety | 9.67 | Average Score (0-10) | 91.8 |
| Arabic Broad Leaderboard - Reasoning & Math | 9.33 | Average Score (0-10) | 89.1 |
| Arabic Broad Leaderboard - RAG QA | 9 | Average Score (0-10) | 88.3 |
| SimpleBench | 79.2 | Score (AVG@5) | 86.3 |
| Tinybird AI SQL Benchmark - Exactness | 53.91 | Result exactness vs human reference queries (0-100) | 79.6 |
| Arabic Broad Leaderboard - General Knowledge | 8.65 | Average Score (0-10) | 55.5 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 94 | Questions answered with a valid query on the first attempt ( | 52.9 |
Interactive version: theaggregate.ai/model?slug=gpt-6-2-astra-pro · How It Works · Data refreshed daily, snapshot 2026-11-20.