OpenAI · model

GPT-6.1 Sol (high) benchmark scores

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

As of 2026-10-07, GPT-6.1 Sol (high) (OpenAI) has measured scores on 1 benchmark and estimated scores on 1 more.

Benchmark	Score	Source
GDP.pdf	32.0%	measured
MMMU-Pro	86.7%	estimated ± 2.6 pp, high confidence