Models Like Claude 3.7 Sonnet
DeepSeek-R1
Model
9.18
Excellent
Gemini 2.5 Pro
Model
9.12
Excellent
Grok-3
Model
8.72
Great
o3-mini
Model
8.62
Great
Gemini 2.5 Flash
Model
8.72
Great
QwQ-32B
Model
8.58
Great
Phi-4
Model
8.28
Great
Command A
Model
8.25
Great
Claude 3.5 Haiku
Model
8.18
Great
o1-mini
Model
8.18
Great
PaLM 2
Model
7.88
Good
Claude 3 Haiku
Model
7.86
Good
Orca 2
Model
7.35
Good
Marco-o1
Model
7.25
Good
Skywork-o1
Model
7.20
Good
Reflection 70B
Model
5.20
Mediocre
Chinchilla
Model
9.02
Excellent
DeepSeek-V3
Model
9.02
Excellent
Llama 3.1 405B
Model
8.88
Great
GPT-3
Model
8.72
Great
InstructGPT
Model
8.70
Great
Qwen2.5
Model
8.62
Great
Mamba
Model
8.62
Great
Wan 2.1
Model
8.55
Great