Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Outcome on Legal Outcome
Loading...
4
OLR
RAG
-0.16
0.92
2
3.08
May 13, 2026
OLR
Performance
Coverage
Updated 14d ago
Evaluation Results
Method
Method
Links
OLR
Performance
Coverage
RAG
Backbone=Qwen3.5-35B-A3B
2026.05
4
89
81.4
RAG
Backbone=Qwen3-30B-A3B
2026.05
3.2
87.5
85.8
Temporal Hint
Backbone=Qwen3-30B-A3B
2026.05
2.2
75.7
61.7
Temporal Hint
Backbone=Qwen3.5-35B-A3B
2026.05
2.1
67.5
69
TimeSPEC
Backbone=Qwen3.5-35B-A3B
2026.05
0.8
81.1
73
TEMPO
Backbone=Qwen3-30B-A3B
2026.05
0.7
80.4
75.7
TEMPO
Backbone=Qwen3.5-35B-A3B
2026.05
0.6
74.1
74.1
TimeSPEC
Backbone=Qwen3-30B-A3B
2026.05
0.1
82.4
65.2
Control
Backbone=Qwen3-30B-A3B
2026.05
0
70.7
66.2
Control
Backbone=Qwen3.5-35B-A3B
2026.05
0
64.7
74.3
Feedback
Search any
task
Search any
task