AICreatorHub

🏆 AI Model Leaderboard

Every model ranked by benchmark score. Switch modality and benchmark to see who's on top right now.

1
Claude Fable 5
95
2
Claude Opus 4.8
94
3
GPT-5.5
94
4
Gemini 3.1 Pro
94
5
GPT-5.4
93
6
GLM-5.2
91
7
DeepSeek V4-Pro
90
8
Qwen3.5-397B
88
9
Qwen3-235B
78
10
Claude Sonnet 4.6
71
11
Mistral Small 4
71
12
Magistral Small 1.2
70
13
Mistral Large 3
67
14
Llama 4 Maverick
66

Scores are widely-reported public benchmark figures (higher is better) for relative ranking — they vary by source and testing methodology. Check the provider for official results.