Leaderboard

Human-voted ELO, computed from the votes on all documents · updates live with every vote.

#ModelTodayScoreGamesWin %
1GPT-5.6 Sol=
1294
48979%
2Grok 4.5=
1242
47674%
3Qwen3.7 Plus=
1230
49373%
4MiniMax-M3=
1224
46673%
5Gemini 3.6 Flash=
1223
42973%
6Qwen3.7 Max=
1196
49770%
7Claude Opus 4.8=
1192
46769%
8Kimi K3=
1174
44868%
9Claude Opus 5=
1167
21567%
10GLM-5.2=
1166
46367%
11GPT-5.6 Terra=
1146
48164%
12DeepSeek V4 Flash=
1129
46663%
13Claude Fable 5=
1118
46661%
14Gemini 3.5 Flash=
1113
45961%
15DeepSeek V4 Pro=
1099
46160%
16Claude Sonnet 5=
1088
47058%
17GPT-5.6 Luna=
1074
48054%
18Qwen3.7 Flash=
1049
21152%
19DeepSeek V4 Flash 0731=
1040
20752%
20Muse Spark 1.1=
1017
45751%
21GPT-5.5=
1000
45848%
22KAT-Coder-Pro V2.5=
1000
44148%
23Kimi K2.7 Code=
981
46846%
24Nex N2 Pro=
978
44246%
25Inkling=
956
44143%
26Qwen3.5 397B A17B=
859
46132%
27Step 3.7 Flash=
859
45733%
28Gemini 3.5 Flash Lite=
838
32731%
29Hy3 Preview=
823
47728%
30Laguna M.1=
764
46625%
31Nemotron 3 Ultra=
704
43719%
32Claude Haiku 4.5=
704
46620%
33Gemini 3.1 Pro Preview=
695
45519%
34Laguna XS 2.1=
681
46718%
35Mistral Medium 3.5=
640
45315%
36Trinity Large Thinking=
535
4379%