Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Benchmarks · reasoning

AI Chess Leaderboard (Dubesor)

LLMs play full chess games against each other from the move list, in reasoning and continuation modes combined; Elo within this LLM-only pool, models with 10+ games.

203 models · 203 results · updated 2026-10-31 · dubesor.de ↗

Leaderboard

Chart settings
203 of 203 selected
Gemini 3.1 Pro high

More from this benchmark

3 published measures

Breakdown

darker is better within each column · click a column to sort

All results

203 rows
#ModelEffortScore
1Gemini 3.1 Prohigh1856 ±84
2Gemini 3 Prohigh1834 ±100
3Gemini 3.8 Flashmax1809 ±105
4Gemini 3.7 Flashmax1807 ±111
5Gemini 3.6 Flashxhigh1750 ±103
6Gemini 3.5 Flashxhigh1715 ±84
7GPT-6 Astramax1640 ±84
8Gemini 4 Argonmax1630 ±98
9GPT-5.1 Codexmax1611 ±98
10GPT-5 Codexhigh1602 ±139
11Gemini 3 Flashhigh1583 ±69
12Opus 5.5max1570 ±94
13GPT-5.5xhigh1568 ±88
14GPT-5high1514 ±93
15o3high1496 ±79
16GPT-6.1 Solmax1493 ±92
17GPT-6.1 Terramax1490 ±99
18Fable 5max1465 ±88
19GPT-5.6 Solmax1459 ±70
20GPT-4.51454 ±155
21DeepSeek V4 Flash 0731max1444 ±97
22Kimi K3max1444 ±103
23GPT-5.1high1442 ±101
24DeepSeek V4 Pro 0813max1432 ±119
25Qwen 3.8 Maxmax1430 ±101
26Grok 4high1415 ±118
27Gemini 3.1 Flash-Litehigh1403 ±78
28Grok 4.20xhigh1362 ±89
29DeepSeek V4.1 Flash 1017max1359 ±104
30DeepSeek V4.1 Flashmax1353 ±104