Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fact-checking on CheckCOVID
Loading...
60
Accuracy
ToE
20.48
30.74
41
51.26
Jun 26, 2026
Accuracy
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy
ToE
Backbone=DeepSeek-V3.2
2026.06
60
TELLER
Backbone=DeepSeek-V3.2
2026.06
56
ZCoT
Backbone=DeepSeek-V3.2
2026.06
52
TELLER
Backbone=GPT-OSS-20B
2026.06
52
ToE
Backbone=GPT-OSS-20B
2026.06
48
STEEL
Backbone=GPT-OSS-20B
2026.06
46
ZCoT
Backbone=GPT-OSS-20B
2026.06
44
DefGen
Backbone=GPT-OSS-20B
2026.06
40
STEEL
Backbone=DeepSeek-V3.2
2026.06
40
AFacTA
Backbone=DeepSeek-V3.2
2026.06
36
DefGen
Backbone=DeepSeek-V3.2
2026.06
36
Adsent
Backbone=DeepSeek-V3.2
2026.06
36
AFacTA
Backbone=GPT-OSS-20B
2026.06
32
Direct
Backbone=DeepSeek-V3.2
2026.06
28
Direct
Backbone=GPT-OSS-20B
2026.06
26
Adsent
Backbone=GPT-OSS-20B
2026.06
22
Feedback
Search any
task
Search any
task