List your company

Reasoning on STB24

83.3Exact Match (EM)STAR (Claude Sonnet 4.6)
7.27627.01346.7566.487May 11, 2026

Evaluation results

MethodLinks
STAR (Claude Sonnet 4.6)Framework=STAR, Params=–, Lat=14.0, Tok=5,5002026.0583.3
STAR (Qwen3-8B)Framework=STAR, Params=8B, Lat=1.6, Tok=4,1912026.0576.3
STARBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0576.3
STAR (Claude Haiku 4.5)Framework=STAR, Params=–, Lat=8.9, Tok=4,0732026.0576.1
STAR (GPT-OSS-20B)Framework=STAR, Params=20B, Lat=7.1, Tok=5,3122026.0571.8
STAR (Ministral-3-8B)Framework=STAR, Params=8B, Lat=1.9, Tok=4,6252026.0566.8
GPT-OSS-20BFramework=LLM-only, Params=20B2026.0551.4
STAR (GLM-4-9B)Framework=STAR, Params=9B, Lat=1.8, Tok=3,7462026.0548.4
STAR (Llama-3.1-8B)Framework=STAR, Params=8B, Lat=2.2, Tok=4,1612026.0548.2
Claude Sonnet 4.6Framework=LLM-only, Params=–2026.0545.2
STAR (Llama-3.2-3B)Framework=STAR, Params=3B, Lat=1.3, Tok=4,0132026.0543.1
ReflexionBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0537.2
GLM-4-9BFramework=LLM-only, Params=9B2026.0537
LLM-only (CoT)Backbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0534.2
Ministral-3-8BFramework=LLM-only, Params=8B2026.0532.1
Qwen3-8BFramework=LLM-only, Params=8B2026.0531.9
LLM-onlyBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0531.9
ReActBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0531.8
Llama-3.1-8BFramework=LLM-only, Params=8B2026.0531.5
Claude Haiku 4.5Framework=LLM-only, Params=–2026.0528.7
Llama-3.2-3BFramework=LLM-only, Params=3B2026.0522.3
Function-callingBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0520.8
Tree-of-ThoughtBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0511.8
Graph-of-ThoughtBackbone=Qwen3-8B, Query Eligibility=EM-eligible queries2026.0510.2