AI Model Leaderboards

Explore various benchmarks and see how different AI models perform against each other.

Intelligence vs. Seconds to Output 500 Tokens, including reasoning model 'thinking' time by Gemini Endpoint

More →

Rank Model Score Organization
1 GPT-5 (high) 69.00 OpenAI
2 Grok 4 67.50 xAI
3 GPT-5 (medium) 67.50 OpenAI
4 O3 Pro 67.10 OpenAI
5 O3 Mini 67.10 OpenAI
6 o3 67.10 OpenAI
7 o4-mini (high) 65.00 OpenAI
8 Gemini 2 5 Pro 05 06 64.60 Google
9 Gemini 2.5 Pro 64.60 Google
10 Gemini 2 5 Pro 03 25 64.60 Google

Tokens used to run all evaluations in the Artificial Analysis Intelligence Index by Gemini Endpoint

More →

Rank Model Score Organization
No scores available for this leaderboard yet.