List your company

Overall Certainty Distortion Analysis on SPICED and MIMIC

49.4Average MetricLlama 3.3
29.22434.46239.744.938Jun 6, 2026

Evaluation results

MethodLinks
Llama 3.3size=70B, sampling=top-p=0.9, T=12026.0649.4
Gemini 3.1version=fl, sampling=top-p=0.9, T=12026.0646.7
Claude 4.5version=H, sampling=top-p=0.9, T=12026.0643
Qwen3size=8B, sampling=top-p=0.9, T=12026.0637.5
gpt-5-nanosampling=top-p=0.9, T=12026.0630