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

CSQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Commonsense ReasoningCSQA
Accuracy96
366
Commonsense ReasoningCSQA
CSQA Accuracy91.2
195
Commonsense Question AnsweringCSQA (test)
Accuracy0.953
127
Commonsense ReasoningCSQA (test)
Accuracy89.4
123
Hallucination DetectionCSQA
AUROC85.1
107
Commonsense Question AnsweringCSQA
Accuracy88.9
71
Question AnsweringCSQA (test)
Accuracy87.2
68
Commonsense Question AnsweringCSQA
Accuracy82.72
61
Prompt InjectionCSQA
ASR@318.33
52
Question AnsweringCSQA
Accuracy88
42
Prompt InjectionCSQA
ASR62
36
Commonsense ReasoningCSQA OOD (test)
Accuracy82.1
32
Commonsense ReasoningCSQA
Task Success Rate (TSR)82.5
30
Malicious AgentCSQA
ASR@30.49
28
Commonsense Question AnsweringCSQA
Accuracy98.9
26
Retrieval-augmented ReasoningCSQA
Accuracy85.42
25
Question AnsweringCSQA
Accuracy (CSQA)86.7
24
Memory AttackCSQA
ASR@31.67
24
CalibrationCSQA
ECE1.04
22
Question AnsweringCSQA (in-domain)
Accuracy86.8
22
Commonsense ReasoningCSQA
Accuracy88.1
20
General Knowledge QACSQA
Accuracy84.1
18
Commonsense ReasoningCSQA
Accuracy (CSQA)66.4
18
Commonsense Question AnsweringCSQA
PIQA84.06
18
Question AnsweringCSQA
ECE1.57
16
Showing 25 of 77 rows