List your company

Logical Reasoning on AR-LSAT

91.7AccuracyVERGE Full
16.674436.152255.6375.1078Oct 8, 2025Nov 3, 2025Nov 30, 2025Dec 27, 2025Jan 23, 2026Feb 19, 2026Mar 18, 2026

Evaluation results

MethodLinks
VERGE Fullbackbone=GPT-120B2026.0191.7
VERGE Fullbackbone=GPT-20B2026.0189.5
SCbackbone=GPT-20B2026.0189.1
SCbackbone=GPT-120B2026.0188.7
VERGE Fullbackbone=Sonnet-3.72026.0188.6
VERGE w/o MCSbackbone=Sonnet-3.72026.0188.2
CoTbackbone=GPT-120B2026.0187.8
VERGE w/o Rtbackbone=Sonnet-3.72026.0187.7
VERGE w/o Rtbackbone=GPT-120B2026.0187.4
VERGE w/o Rtbackbone=GPT-20B2026.0186.8
SRbackbone=GPT-120B2026.0184.8
VERGE w/o MCSbackbone=GPT-120B2026.0183
D&PParadigm=AF, Fallback Policy=CoT, LLM=GPT-4o2026.0382.83
VERGE w/o MCSbackbone=GPT-20B2026.0182.6
CoTbackbone=GPT-20B2026.0181.7
D&PParadigm=AF, Fallback Policy=CoT, LLM=GPT-42026.0380.65
D&PParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-42026.0378.43
D&PParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-4o2026.0378
SRbackbone=Sonnet-3.72026.0173.5
DSBbackbone=Sonnet-3.72026.0167.8
SRbackbone=GPT-20B2026.0163.9
CLOVERParadigm=AF, Fallback Policy=CoT, LLM=GPT-4o2026.0362.8
Loc. uniBackbone=DS-R1-Distill-Qwen-7B2025.1062
Glob. non-uniBackbone=DS-R1-Distill-Qwen-7B2025.1062
CoTbackbone=Sonnet-3.72026.0161.7
DSBbackbone=GPT-20B2026.0159.6
SCbackbone=Sonnet-3.72026.0158.7
Mean Acc.Backbone=DS-R1-Distill-Qwen-7B2025.1055
MAD-LOGICParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-42026.0353.25
Self-Cert.Backbone=DS-R1-Distill-Qwen-7B2025.1051
High Conf.Backbone=DS-R1-Distill-Qwen-7B2025.1051
Low Ent.Backbone=DS-R1-Distill-Qwen-7B2025.1051
Glob. non-uniBackbone=DS-R1-Distill-Llama-8B2025.1049
Loc. non-uniBackbone=DS-R1-Distill-Qwen-7B2025.1048
CLOVERParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-4o2026.0346.8
Logic-LM++Paradigm=AF, Fallback Policy=CoT, LLM=GPT-42026.0346.32
Loc. uniBackbone=DS-R1-Distill-Llama-8B2025.1046
Glob. uniBackbone=DS-R1-Distill-Qwen-7B2025.1046
LINCParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-4o2026.0344.65
Self-Cert.Backbone=DS-R1-Distill-Llama-8B2025.1044
SymbCoTParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-42026.0343.91
Logic-LMParadigm=AF, Fallback Policy=CoT, LLM=GPT-42026.0343.04
Mean Acc.Backbone=DS-R1-Distill-Llama-8B2025.1043
High Conf.Backbone=DS-R1-Distill-Llama-8B2025.1043
Low Ent.Backbone=DS-R1-Distill-Llama-8B2025.1042
Glob. uniBackbone=DS-R1-Distill-Llama-8B2025.1040
Loc. non-uniBackbone=DS-R1-Distill-Llama-8B2025.1039
CoT-SCParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-4o2026.0338.37
LINCParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-42026.0337.83
CoTParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-4o2026.0336.09
CoTParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-42026.0335.06
SymbCoTParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-4o2026.0334.2
DirectParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-42026.0333.3
DSBbackbone=GPT-120B2026.0132.2
LogicLMbackbone=Sonnet-3.72026.0131.2
DirectParadigm=Prompting, Fallback Policy=N/A, LLM=GPT-4o2026.0330.3
LogicLMbackbone=GPT-20B2026.0121.7
Logic-LM++Paradigm=AF, Fallback Policy=Abstention (None), LLM=GPT-42026.0321.18
LogicLMbackbone=GPT-120B2026.0119.9
Logic-LMParadigm=AF, Fallback Policy=Abstention (None), LLM=GPT-42026.0319.56