ChessBench

[PREVIEW]

A New Chess Benchmark for Language Models

Changes

May 2026

2026-05-20

  • added gemini-3.5-flash
  • updated elo formula

2026-05-15

  • added chessbench.ai/changes

2026-05-11

  • officially announced chessbench.ai

2026-05-07

  • added:
    • gpt-5
    • gpt-5-mini
    • gpt-5-nano

2026-05-02

  • added:
    • o3
    • o3-mini
    • o4-mini

2026-05-01

  • added claude-opus-4-7

April 2026

2026-04-30

  • added:
    • claude-sonnet-4-6
    • claude-opus-4-6
    • gpt-4.1-mini
    • gpt-4.1-nano

2026-04-28

  • added:
    • gpt-4o-2024-05-13
    • gpt-4o-2024-08-06
    • gpt-4o-2024-11-20

2026-04-27

  • added chessbench.ai/timeline

2026-04-26

  • added chessbench.ai/leaderboard
  • added:
    • gpt-3.5-turbo-0125
    • gpt-4-0613
    • gpt-4-turbo-2024-04-09

2026-04-21

  • added:
    • gemini-3.1-flash-lite-preview
    • claude-opus-4-1-20250805
    • claude-haiku-4-5-20251001
    • claude-sonnet-4-5-20250929
    • claude-opus-4-5-20251101

2026-04-19

  • silently launched chessbench.ai in preview mode, with the following models:
    • gemini-2.0-flash
    • gemini-2.0-flash-lite
    • gemini-2.5-flash
    • gemini-2.5-flash-lite
    • gemini-2.5-pro
    • gemini-3-flash-preview
    • claude-sonnet-4-20250514
    • claude-opus-4-20250514