Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Reasoning on CaseHold (Accuracy)
Loading...
83.13
Accuracy (CaseHold)
XPERT-DeepSeek
78.3148
79.5649
80.815
82.0651
May 9, 2026
Accuracy (CaseHold)
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy (CaseHold)
XPERT-DeepSeek
#Params=270M
2026.05
83.13
XPERT-OLMoE
#Params=270M
2026.05
83.11
XPERT-OLMoE
#Params=570M
2026.05
82.96
XPERT-OLMoE
#Params=480M
2026.05
82.9
Distillation
#Params=270M
2026.05
82.54
XPERT-DeepSeek
#Params=570M
2026.05
82.54
XPERT-DeepSeek
#Params=480M
2026.05
82.12
XPERT-OLMoE
#Params=391M
2026.05
81.5
Distillation
#Params=480M
2026.05
81.35
Distillation
#Params=570M
2026.05
81.35
XPERT-DeepSeek
#Params=391M
2026.05
81.1
Scratch
#Params=480M
2026.05
80.97
Scratch
#Params=270M
2026.05
80.93
Distillation
#Params=391M
2026.05
80.48
Scratch
#Params=570M
2026.05
80.16
Scratch
#Params=391M
2026.05
78.5
Feedback
Search any
task
Search any
task