Loading...
Loading...
ARC-AGI-1
Twitter30
Total Models
28.15
Average Score
0.00 - 75.70
Score Range
1
Max Score Achievable
Top 10 Model Performance
Top 10 of 30
Models Using This Benchmark(30)
OpenAI(16 models)
o3 Preview
openai
75.70%
GPT-5
openai
65.70%
o3 Pro
openai
59.30%
GPT-5 mini
openai
54.30%
o3
openai
53.00%
o4 Mini
openai
41.80%
o3-mini
openai
34.50%
o1
openai
30.70%
Codex Mini
openai
27.30%
o1 pro
openai
23.30%
GPT-5 nano
openai
16.70%
o1 mini
openai
14.00%
GPT-4.5
openai
10.30%
GPT-4.1
openai
5.50%
GPT-4.1 Mini
openai
3.50%
GPT-4.1 Nano
openai
0.00%
Anthropic(3 models)
xAI(3 models)
Meta(2 models)
Llama 4 Maverick
meta
4.40%
Llama 4 Scout
meta
0.50%
Mistral(2 models)
Magistral Medium
mistral
6.10%
Magistral Small
mistral
5.00%
Google(1 model)
Gemini 2.5 Pro Preview
google
41.00%
Qwen(1 model)
41.80%