GPT-6.2 Sol (Medium): benchmark results

Provider: OpenAI. Released 2026-11-17. Access: API.

Aggregate Rating 1954 ± 13, rank #22 of 2274 rated models, from 121 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Maze-Bench96.61Mean Score100
AA GDP.pdf - Construction - Criterion Pass Rate83.53Criterion Pass Rate (%)97.8
AA GDP.pdf - Finance/Investing - Criterion Pass Rate91.5Criterion Pass Rate (%)96.7
AA GDP.pdf - Engineering - Criterion Pass Rate84.99Criterion Pass Rate (%)96.4
MLCR-AA - Accuracy95Accuracy (%)95.1
DeepsecBench44.74Recall-weighted F2 score (%)94.9
AA GDP.pdf - Insurance - Criterion Pass Rate87.57Criterion Pass Rate (%)94.2
AA Terminal-Bench Science 0.1 - Engineering Sciences66.67Pass@1 (%)93.9
AA GDP.pdf29.2All Criteria Pass Rate (%)93.6
AA Terminal-Bench Science 0.1 - Earth Sciences66.67Pass@1 (%)93.6
AutomationBench-AA - Strict41.4Strict Task Success (%)93.1
AutomationBench-AA70.28Guardrail-Adjusted Objective Completion (%)92.4

Interactive version: theaggregate.ai/model?slug=gpt-6-2-sol-medium · How It Works · Data refreshed daily, snapshot 2026-11-18.