Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Reasoning on PRBench Legal-Hard
Loading...
0.377
GPT-5 Grader Score
Qwen3.5-4B RL
0.23556
0.27228
0.309
0.34572
Jun 24, 2026
GPT-5 Grader Score
Kimi-K2.6 Grader Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
GPT-5 Grader Score
Kimi-K2.6 Grader Score
Qwen3.5-4B RL
Training Data=Agentic...
2026.06
0.377
0.331
Qwen3.5-397B
RL=No RL
2026.06
0.341
0.294
Qwen3.5-4B RL
Training Data=CoT Self...
2026.06
0.32
0.3
Qwen3.5-4B
RL=No RL
2026.06
0.241
0.219
Feedback
Search any
task
Search any
task