Share your thoughts, 1 month free Claude Pro on usSee more

Reasoning on STARK

79.3EM

STAR (Claude Sonnet 4.6)

Updated 22d ago

Evaluation Results

Method	Links
STAR (Claude Sonnet 4.6) 2026.05		79.3
STAR (GPT-OSS-20B) 2026.05		75.1
STAR (Claude Haiku 4.5) 2026.05		74.6
STAR (Qwen3-8B) 2026.05		73
STAR 2026.05		73
Claude Sonnet 4.6 2026.05		71.4
Claude Haiku 4.5 2026.05		70.3
Reflexion 2026.05		68.8
GPT-OSS-20B 2026.05		67.9
STAR (Llama-3.1-8B) 2026.05		67.8
ReAct 2026.05		65.6
STAR (GLM-4-9B) 2026.05		65.3
STAR (Ministral-3-8B) 2026.05		64.1
Tree-of-Thought 2026.05		62.8
Graph-of-Thought 2026.05		61.7
LLM-only (CoT) 2026.05		59.4
Qwen3-8B 2026.05		55.4
LLM-only 2026.05		55.4
GLM-4-9B 2026.05		52.9
STAR (Llama-3.2-3B) 2026.05		51.8
Ministral-3-8B 2026.05		51.3
Llama-3.1-8B 2026.05		50.4
Llama-3.2-3B 2026.05		41.8
Function-calling 2026.05		31.9