List your company

Question-Type Diversity Alignment on Legalbench Taxonomy

0.036Jensen Shannon Divergencegpt-oss-120b
0.03220.057850.08350.10915Mar 5, 2026

Evaluation results

MethodLinks
gpt-oss-120bSimulator Variant=AGENT2026.030.036
gpt-oss-120bSimulator Variant=SCOTUS_DEFAULT2026.030.061
gpt4oSimulator Variant=SCOTUS_DEFAULT2026.030.069
gemini-2.5-proSimulator Variant=AGENT2026.030.072
gemini-2.5-proSimulator Variant=SCOTUS_DEFAULT2026.030.087
Llama-3.3-70B-InstructSimulator Variant=SCOTUS_DEFAULT2026.030.122
gpt4oSimulator Variant=AGENT2026.030.124
Qwen3-32BSimulator Variant=SCOTUS_DEFAULT2026.030.131