Loading...
Loading...
SimpleBench
Twitter34
Total Models
33.17
Average Score
10.70 - 62.40
Score Range
1
Max Score Achievable
Top 10 Model Performance
Top 10 of 34
Models Using This Benchmark(34)
OpenAI(12 models)
GPT-5
openai
56.70%
o3
openai
53.10%
o1 preview
openai
41.70%
o1
openai
40.10%
o4 Mini
openai
38.70%
GPT-4.5
openai
34.50%
GPT-4.1
openai
27.00%
GPT-4 Turbo
openai
25.10%
o3-mini
openai
22.80%
o1 mini
openai
18.10%
GPT-4o
openai
17.80%
GPT-4o-mini
openai
10.70%
Anthropic(7 models)
Claude Opus 4.1
anthropic
60.00%
Claude Opus 4
anthropic
58.80%
Claude 3.7 Sonnet
anthropic
46.40%
Claude Sonnet 4
anthropic
45.50%
Claude 3.5 Sonnet
anthropic
41.40%
Claude 3.5 Sonnet
anthropic
27.50%
Claude 3 Opus
anthropic
23.50%
DeepSeek(4 models)
Google(3 models)
Meta(3 models)
Cohere(1 model)
Command R+
cohere
17.40%
Mistral(1 model)
Mistral Large 2
mistral
22.50%
Qwen(1 model)
Qwen3 235B A22B
qwen
31.00%