Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Common sense Reasoning on mCSQA (test)
Loading...
90.8
EN Accuracy
L8b_T
87.264
88.182
89.1
90.018
Jan 22, 2026
EN Accuracy
DE Accuracy
FR Accuracy
JA Accuracy
ZH Accuracy
Overall Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
EN Accuracy
DE Accuracy
FR Accuracy
JA Accuracy
ZH Accuracy
Overall Accuracy
L8b_T
Merging Technique=TIES...
2026.01
90.8
83.2
76
77.4
72.4
80
L8b_DTS
Merging Technique=DARE...
2026.01
89.8
82.4
75.6
75.8
73.6
79.4
L8b_TS
Merging Technique=TIES...
2026.01
89.8
82.4
75.6
75.8
73.6
79.4
L8b_COMB
Protocol=COMB, Backbon...
2026.01
89.6
84
75.4
75.4
73.2
79.5
L8b_INDV
Protocol=INDV, Backbon...
2026.01
87.6
83.6
77
75.8
72.4
79.3
L8b_DT
Merging Technique=DARE...
2026.01
87.4
82.2
75.2
77.6
70.8
78.6
Feedback
Search any
task
Search any
task