Skip to main content
Evaluation sources/Chess Puzzles
ParticipatingReasoning

Chess Puzzles

Epoch AI · Public model evaluation results from Chess Puzzles.

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

Claude Fable 5.20.7984.62026-11-10
Gemini 4 Carbon0.7883.82026-11-11
GPT-6 Astra0.7480.62026-11-05
GPT-6.1 Sol0.6875.72026-11-05
Claude Opus 5.50.6774.92026-11-05
Claude Opus 5.50.6774.92026-10-18
Claude Opus 5.50.6774.92026-10-17
GPT-5.50.6371.72026-11-05
GPT-5.5 Pro0.6270.92026-10-17
GPT-5.5 Pro0.6270.92026-11-05
GPT-5.5 Pro0.6270.92026-10-18
GPT-5.2 Pro0.669.22026-10-18
GPT-5.2 Pro0.669.22026-11-05
GPT-5.2 Pro0.669.22026-10-17
Claude Sonnet 5.50.5968.42026-10-17
Claude Sonnet 5.50.5968.42026-10-18
Claude Sonnet 5.50.5968.42026-11-05
Gemini 4 Argon0.5968.42026-11-05
Gemini 4 Argon0.5968.42026-10-18
Gemini 4 Argon0.5968.42026-10-17
GPT-5.4 Pro0.5968.42026-11-05
GPT-5.6 Sol0.5968.42026-11-05
Gemini 3.8 Flash0.5867.62026-11-05
GPT-6 Sol0.5666.02026-10-17

Page 1 of 6

Frequently asked questions