GPT-6.1 Sol: benchmark results
Provider: OpenAI. Released 2026-09-29. Access: API.
Aggregate Rating 1959 ± 7, rank #9 of 1640 rated models, from 411 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GDP.pdf - Construction - Criterion Pass Rate | 84.94 | Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - Criterion Pass Rate | 82.86 | Macro Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - Real Estate - Criterion Pass Rate | 81.5 | Criterion Pass Rate (%) | 100 |
| AI Coding Daily (Codex CLI) - Laravel Code Quality | 19.1 | Laravel Code Quality (max 20) points, LLM-judged rubric scor | 100 |
| AI Coding Daily (Codex CLI) - React-TS Code Quality | 19 | React-TS Code Quality (max 20) points, LLM-judged rubric sco | 100 |
| AI Coding Daily (Codex CLI) - Total | 68.1 | Total points (max 70) | 100 |
| BrickBench (Overall, BrickAgent) - Alignment Elo | 1301 | Alignment Elo (rating); published Overall cohort | 100 |
| CMDB-1500 (Text) | 80 | Accuracy (%), fixed denominator of 1,200 questions (invalid | 100 |
| Chatbot Arena (Vision - Homework) | 1355 | Arena Score | 100 |
| EnigmaForge | 84.5 | Task success (%) over 600 procedurally generated story insta | 100 |
| EnigmaForge - Fact F1 | 98.5 | World-fact recovery F1 (%) over 600 instances, all items | 100 |
| EnigmaForge - Intuition | 83.8 | Task success (%) on implicit-condition instances, where the | 100 |
Interactive version: theaggregate.ai/model?slug=gpt-6-1-sol · How It Works · Data refreshed daily, snapshot 2026-10-13.