GPT-6 Pro Sol: benchmark results
Provider: OpenAI. Access: API.
Aggregate Rating 1908 ± 10, rank #18 of 10916 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ObviousBench | 100 | Answer pass³ (%) | 96.8 |
| MineBench | 2075 | Elo Rating | 94.7 |
| AIMultiple - Agentic RAG Routing | 84.24 | Routing accuracy (%, 184 hardest of 759 BIRD questions, 11 d | 88.8 |
| AIMultiple - Text-to-SQL (Adjudicated) | 78.3 | Execution match with jury-credited equivalents and broken go | 81.2 |
| AIMultiple - Text-to-SQL (Strict Execution Match) | 43.6 | Execution match against BIRD gold (%, over correctly routed | 71.2 |
| Tinybird AI SQL Benchmark - Exactness | 51.57 | Result exactness vs human reference queries (0-100) | 69.7 |
| Bullshit Benchmark | 38.2 | BS Detection Rate (%) | 64.1 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 90 | Questions answered with a valid query on the first attempt ( | 35.1 |
| Tinybird AI SQL Benchmark - Success Rate | 98 | Questions answered with a valid query within 3 retries (%) | 35.1 |
Interactive version: theaggregate.ai/model?slug=gpt-6-pro-sol · How It Works · Data refreshed daily, snapshot 2026-11-08.