Loading...
Loading...
ARC-AGI-2
Twitter28
Total Models
2.82
Average Score
0.00 - 16.20
Score Range
1
Max Score Achievable
Top 10 Model Performance
Top 10 of 28
Models Using This Benchmark(28)
OpenAI(16 models)
GPT-5
openai
9.90%
o3 Pro
openai
4.90%
GPT-5 mini
openai
4.40%
o3 Preview
openai
4.00%
o3
openai
3.00%
o3-mini
openai
3.00%
GPT-5 nano
openai
2.60%
o4 Mini
openai
2.40%
Codex Mini
openai
1.30%
o1
openai
1.30%
o1 pro
openai
0.90%
GPT-4.5
openai
0.80%
o1 mini
openai
0.80%
GPT-4.1
openai
0.40%
GPT-4.1 Mini
openai
0.00%
GPT-4.1 Nano
openai
0.00%
Anthropic(3 models)
Meta(2 models)
Llama 4 Maverick
meta
0.00%
Llama 4 Scout
meta
0.00%
Mistral(2 models)
Magistral Medium
mistral
0.00%
Magistral Small
mistral
0.00%
xAI(2 models)
Grok 4
x-ai
16.20%
Grok 3 Mini
x-ai
0.40%
Google(1 model)
Gemini 2.5 Pro Preview
google
4.90%