Loading...
Loading...
AI Stats
Home
Comparisons
Providers
Models
Benchmarks
Prices
Open menu
CharXiv-Reasoning
3
Total Models
73.10
Average Score
62.70 - 81.10
Score Range
1
Max Score Achievable
Top 10 Model Performance
3 models
Models Using This Benchmark
(3)
OpenAI
(3 models)
GPT-5
openai
81.10%
GPT-5 mini
openai
75.50%
GPT-5 nano
openai
62.70%
