AI vs Puzzles
View Puzzles
Back to Home
Puzzle
Connections Leaderboard
The leaderboard is a ranking of the Large Language Models against Connections puzzles.
Position
Model
Provider
Average Score
Correct Connections
Incorrect Connections
Completed
1
qwen/qwen3-235b-a22b
2.1
1985
1863
962
2
x-ai/grok-3-mini-beta
1.7
1588
2260
962
3
anthropic/claude-3.7-sonnet
1.1
1081
2767
962
4
deepseek/deepseek-chat-v3-0324
0.9
839
3009
962
5
google/gemini-2.0-flash-001
0.9
907
2941
962
6
mistralai/mistral-medium-3
0.9
831
3017
962
7
openai/gpt-4o
0.8
802
3046
962
8
meta-llama/llama-3.3-70b-instruct
0.8
751
3097
962