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
gemini-2.5-pro
gemini-2.5-pro7878
1128.38
-5.73 +5.45
1
gemini-3-pro-preview
gemini-3-pro-preview5675
1124.45
-5.39 +6.48
2
claude-sonnet-4-5-20250929
claude-sonnet-4-5-202509299810
1117.49
-4.2 +4.33
3
claude-sonnet-4-5-20250929 (Thinking)
claude-sonnet-4-5-20250929 (Thinking)9385
1110.68
-4.4 +5.52
4
gpt-5-chat
gpt-5-chat11212
1106.91
-5.12 +5.14
4
qwen3-235b-a22b-2507-v1
qwen3-235b-a22b-2507-v19606
1106.44
-3.4 +3.67
7
claude-opus-4-1-20250805
claude-opus-4-1-2025080512337
1084.25
-4.69 +4.52
7
claude-opus-4-1-20250805 (Thinking)
claude-opus-4-1-20250805 (Thinking)10680
1075.72
-4.01 +4.13
8
claude-haiku-4-5-20251001 (Thinking)
claude-haiku-4-5-20251001 (Thinking)3979
1071.05
-7.16 +5.87
8
claude-sonnet-4-20250514
claude-sonnet-4-2025051417627
1070.56
-3.37 +4.12
8
gemini-2.5-flash
gemini-2.5-flash8040
1069.42
-5.42 +4.29
8
claude-haiku-4-5-20251001
claude-haiku-4-5-202510014100
1068.38
-5.61 +5.7
10
claude-sonnet-4-20250514 (Thinking)
claude-sonnet-4-20250514 (Thinking)13829
1062.97
-4.12 +3.53
14
deepseek-r1-0528
deepseek-r1-05287385
1052.05
-5.09 +5.44
15
18194
1043.66
-2.9 +3.27
16
14340
1014.70
-4.06 +4.62
17
18067
1000.43
-3.54 +3.27
17
llama4-maverick-instruct-basic
llama4-maverick-instruct-basic12442
1000.00
-4.26 +5.21
* 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.
