Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Autonomous LLM Fine-tuning on LawBench
Loading...
51.2
Hybrid Score
Qwen3-235B-2507
23.12
30.41
37.7
44.99
Apr 15, 2026
Hybrid Score
Updated 2d ago
Evaluation Results
Method
Method
Links
Hybrid Score
Qwen3-235B-2507
Model Category=Ref Model
2026.04
51.2
TREX
Researcher Backend=Qwe...
2026.04
42.1
TREX
Researcher Backend=Gem...
2026.04
40.9
Qwen3-1.7B
Model Category=Base Model
2026.04
24.2
Feedback
Search any
task
Search any
task