Loading...
Loading...
EQ-Bench 3
Twitter33
Total Models
1096.00
Average Score
435.10 - 1563.30
Score Range
1
Max Score Achievable
Top 10 Model Performance
Top 10 of 33
Models Using This Benchmark(33)
OpenAI(10 models)
o3
openai
1500.00
GPT-5 chat
openai
1357.10
o4 Mini
openai
1291.00
GPT-4.1
openai
1234.80
gpt-oss-120b
openai
1152.10
GPT-4.1 Mini
openai
1144.50
GPT-4.5
openai
1092.70
GPT-4.1 Nano
openai
903.60
gpt-oss-20b
openai
800.20
GPT-4
openai
435.10
Google(6 models)
Gemini 2.5 Pro Preview
google
1470.20
1284.50
Gemini 2.5 Pro Preview
google
1247.00
Gemma 3 27B
google
1040.70
Gemma 3 4B
google
856.40
Gemini 2.0 Flash
google
775.30
Qwen(5 models)
Anthropic(4 models)
Claude Opus 4
anthropic
1295.60
Claude Sonnet 4
anthropic
1260.80
Claude 3.7 Sonnet
anthropic
1082.70
Claude 3.5 Sonnet
anthropic
1067.70
xAI(3 models)
DeepSeek(2 models)
R1
deepseek
1270.10
DeepSeek-V3 0324
deepseek
1170.40
Mistral(2 models)
Mistral Small 3.2
mistral
1126.50
637.90
Moonshot(1 model)
Kimi K2 Instruct
moonshotai
1563.30