Skip to main content
Evaluation sources/GPQA Diamond
ObservingReasoning

GPQA Diamond

Scale · Public model evaluation results from GPQA Diamond.

Official evaluation
Source description

This source measures concrete delivery performance in Reasoning; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Fugu95.595.52026-08-05
Fugu Ultra95.595.52026-08-05
GPT-5.6 Sol94.694.62026-07-09
GPT-5.4 Pro94.494.42026-04-23
Gemini 3.1 Pro Preview94.394.32026-04-23
Claude Opus 4.794.294.22026-04-23
GPT-5.593.693.62026-04-23
GPT-5.6 Terra92.992.92026-07-09
GPT-5.492.892.82026-04-23
Qwen3.7 Max92.492.42026-05-19
GPT-5.6 Luna92.392.32026-07-09
LongCat-2.088.988.92026-06-30
MiMo-V2.5-Pro86.686.62026-04-22
MAI-Code-1-Flash84.684.62026-08-05

Frequently asked questions