Showdown Leaderboard - LLMs
Real people. Real conversations. Real rankings.
Showdown ranks AI models based on how they perform in real-world use— not synthetic tests or lab settings. Votes are blind, optional, and organic, so rankings reflect authentic preferences.Methodology & Technical Report→0 promptsReal conversation prompts compared across models through pairwise votes.
0 usersFrom 80+ countries and 70+ languages, spanning all backgrounds and professions.
SEAL Leaderboard - LLMs
Style Control
RANK ↑
MODEL ↑↓
VOTES ↑↓
SCORE ↑↓
1
gpt-5.2-chat-latest
gpt-5.2-chat-latest6986
1148.46
-6.71 +4.36
2
gemini-3-flash
gemini-3-flash6194
1135.60
-6.46 +4.53
2
claude-opus-4-5-20251101 (Thinking)
claude-opus-4-5-20251101 (Thinking)5384
1132.04
-4.67 +4.85
2
claude-opus-4-5-20251101
claude-opus-4-5-202511018062
1130.41
-4.27 +4.95
2
gemini-2.5-pro
gemini-2.5-pro12231
1126.17
-4.85 +5.18
2
gemini-3-pro-preview
gemini-3-pro-preview9236
1124.16
-4.67 +6.22
5
claude-sonnet-4-5-20250929
claude-sonnet-4-5-2025092913120
1117.21
-3.34 +4.99
7
claude-sonnet-4-5-20250929 (Thinking)
claude-sonnet-4-5-20250929 (Thinking)13081
1110.94
-3.68 +4.43
8
gpt-5-chat
gpt-5-chat11529
1105.83
-2.97 +5.18
8
qwen3-235b-a22b-2507-v1
qwen3-235b-a22b-2507-v112602
1105.38
-4.08 +4.43
9
gpt-5.1-2025-11-13-medium
gpt-5.1-2025-11-13-medium7953
1097.82
-5.37 +5.06
11
gpt-5.2-2025-12-11-medium
gpt-5.2-2025-12-11-medium6799
1091.55
-6.69 +5.63
11
kimi-k2-thinking
kimi-k2-thinking9487
1088.96
-4.40 +3.96
12
claude-opus-4-1-20250805
claude-opus-4-1-2025080513895
1085.05
-3.06 +2.71
14
deepseek-v3p2
deepseek-v3p28124
1077.81
-5.32 +4.76
14
claude-opus-4-1-20250805 (Thinking)
claude-opus-4-1-20250805 (Thinking)12273
1077.13
-2.92 +5.63
15
claude-haiku-4-5-20251001
claude-haiku-4-5-202510015842
1072.32
-5.14 +6.27
16
claude-sonnet-4-20250514
claude-sonnet-4-2025051421758
1070.18
-2.88 +3.35
16
gemini-2.5-flash
gemini-2.5-flash11787
1069.24
-5.33 +3.93
16
claude-haiku-4-5-20251001 (Thinking)
claude-haiku-4-5-20251001 (Thinking)5734
1068.32
-6.10 +5.75
19
claude-sonnet-4-20250514 (Thinking)
claude-sonnet-4-20250514 (Thinking)13836
1061.98
-3.87 +3.65
22
deepseek-r1-0528
deepseek-r1-052810901
1048.97
-4.66 +4.06
22
21650
1043.71
-3.34 +2.78
24
16606
1012.51
-3.79 +4.05
25
llama4-maverick-instruct-basic
llama4-maverick-instruct-basic12587
1000.00
-3.87 +4.48
25
22231
998.21
-2.48 +3.58
* This model’s API does not consistently return Markdown-formatted responses. Since raw outputs are used in head-to-head comparisons, this may affect its ranking.
