Kaggle Game Arena · Chess

LLM chess leaderboard: which AI is best at chess?

These are general-purpose language models playing chess against each other on Kaggle Game Arena, with no game engines to help. This page covers chess only.

1 record and 1 tracked run or leaderboard for Chess only. Nothing on this page is compared with other games. How we verify.

Which AI is best at chess?

On Kaggle Game Arena: Chess (text), the current #1 is Gemini 3.8 Flash: 1,452 (Elo), as of Oct 15, 2026 (verified, from the official leaderboard). The ladder only includes language models, not dedicated chess engines.

Records

Chess records
ModelAchievementRun configStatusDate
Gemini 3.8 Flash #1 on Kaggle Game Arena Chess: 1452 Elo
Last verified: – · Last checked: Oct 18, 2026
How was this run measured?
Model
Gemini 3.8 Flash
Game
Chess
Project
Kaggle Game Arena
Harness
Kaggle Game Arena text harness (FEN/PGN)
Inputs
board as text
Tools
none (no chess engine)
Assistance
none
Budget
40 games per model pair; per-model reasoning settings not shown
Verification
Verified Read from the official leaderboard, which links replays of every game.
Evidence
Kaggle Game Arena: Chess leaderboard (official) (operator)
Dates
evidence dated Oct 15, 2026
Recorded
published Oct 15, 2026 · discovered by AI vs Games Oct 17, 2026
Changes
No change detected since we started tracking.
Permanent link · Submit a correction · Share card (PNG) · JSON
 Kaggle Game Arena text harness (FEN/PGN)
board as text
 Verified
source
 Oct 15, 2026

Run history

Tracked runs & leaderboards

Kaggle Game Arena: Chess (text) RECENT

Models play chess against each other with no engine help and are ranked by Elo (Bradley–Terry). Each pair of models plays 40 games.

⚠ The Game Arena hub card shows 1499 for #1, which conflicts with the 1452 on the benchmark page. We use the benchmark page.
⚠ Game Arena hub card showed 1499 for #1 (seen Oct 18, 2026). Not found on the chess-text benchmark page (1452, updated Oct 15) or in The Aggregate's Oct 18 snapshot (1451.67). We use the benchmark page.
How was this measured? (applies to every row)
Harness
Kaggle Game Arena text harness (FEN/PGN)
Inputs
board as text
Tools
none (no chess engine)
Assistance
none
Budget
40 games per model pair; per-model reasoning settings not shown
Sources
www.kaggle.com · www.kaggle.com
Submit a correction
#ModelEloStatusAs of
1 Gemini 3.8 Flash
Cross-checked 2026-10-18 13:35 EDT: The Aggregate's daily snapshot (2026-10-18) lists 1451.67. Kaggle's Oct 8 version (v2) showed 1429.
 1,452Verified2026-10-15
2 GPT-6 Astra 1,421Verified2026-10-15
3 Gemini 3.1 Pro Preview 1,315Verified2026-10-15
4 GPT-5.5 1,246Verified2026-10-15
5 Gemini 3.6 Flash 1,222Verified2026-10-15
6 Gemini 3 Flash Preview 1,211Verified2026-10-15
7 GPT-6.1 Sol 1,209Verified2026-10-15
8 GPT-5.6 Sol 1,120Verified2026-10-15
9 GPT-6 Sol 1,008Verified2026-10-15
10 Claude Opus 5.5 965Verified2026-10-15
11 GPT-5.4 897Verified2026-10-15
12 Grok 4.7 845Verified2026-10-15

Last checked: Oct 18, 2026 · auto-update: manual source

More questions about AI and Chess

Is this Elo the same as a human chess rating?

No. Game Arena Elo is calculated only from games between the AI models on this ladder, so it is not a FIDE rating. Dedicated chess engines such as Stockfish are a different kind of program and aren't on this ladder.

This Week in AI vs Games

One short email every Sunday: new records, memorable failures and runs to watch. Free. Every claim is linked to its source.

Preview placeholder. The Beehiiv embed goes here.

Latest issue: Issue #1: The Ender Dragon is down