List your company

Classification on MSciNLI, MNLI, PPDB, Yahoo, HellaSwag, CSQA, AQUA Average

4.34ECECaliDist (As.)
3.09611.49319.8928.287Jun 4, 2026

Evaluation results

MethodLinks
CaliDist (As.)LLM=Phi-4-mini (3.8B)2026.064.3418.13
CaliDist (Sa.)LLM=Gemma-3 (4B)2026.064.420.18
CaliDist (As.)LLM=Gemma-3 (4B)2026.064.5621.01
CaliDist (Pr.)LLM=Phi-4-mini (3.8B)2026.065.0118.03
CaliDist (Sa.)LLM=Phi-4-mini (3.8B)2026.065.2317.88
CaliDist (Pr.)LLM=Gemma-3 (4B)2026.065.3320.4
Temperature ScalingLLM=Phi-4-mini (3.8B)2026.068.0718.75
ConsistencyLLM=Phi-4-mini (3.8B)2026.061622.58
VanillaLLM=Phi-4-mini (3.8B)2026.0616.221.13
FSDLLM=Phi-4-mini (3.8B)2026.0617.0622.36
EntropyLLM=Phi-4-mini (3.8B)2026.0623.6526.71
Temperature ScalingLLM=Gemma-3 (4B)2026.0632.4233.26
ConsistencyLLM=Gemma-3 (4B)2026.0634.2634.96
FSDLLM=Gemma-3 (4B)2026.0634.3534.91
VanillaLLM=Gemma-3 (4B)2026.0635.1135.07
EntropyLLM=Gemma-3 (4B)2026.0635.4435.48