List your company

Mathematical Reasoning on AQuA (ECE and BS)

2.02ECECaliDist (As.)
0.7729.19617.6226.044Jun 4, 2026

Evaluation results

MethodLinks
CaliDist (As.)LLM=LLAMA-3.1 8B2026.062.0217.65
CaliDist (Sa.)LLM=LLAMA-3.1 8B2026.062.7317.25
CaliDist (Pr.)LLM=QWEN-3 8B2026.062.8211.21
CaliDist (Pr.)LLM=LLAMA-3.1 8B2026.062.9817.45
CaliDist (As.)LLM=QWEN-3 8B2026.063.2711.17
CaliDist (Sa.)LLM=QWEN-3 8B2026.063.911.16
ConsistencyLLM=LLAMA-3.1 8B2026.064.8814.51
FSDLLM=QWEN-3 8B2026.067.379.48
Temperature ScalingLLM=QWEN-3 8B2026.068.2810.63
Temperature ScalingLLM=LLAMA-3.1 8B2026.068.7117.11
EntropyLLM=QWEN-3 8B2026.068.910.86
ConsistencyLLM=QWEN-3 8B2026.069.159.63
VanillaLLM=QWEN-3 8B2026.0612.5412.7
CaliDist_verbalized (As.)LLM=QWEN-2 7B2026.0613.7117.68
CaliDist_verbalized (Sa.)LLM=QWEN-2 7B2026.0614.0617.41
CaliDist_verbalized (Pr.)LLM=QWEN-2 7B2026.0614.4417.83
VerbalizedLLM=QWEN-2 7B2026.0616.7417.63
FSDLLM=LLAMA-3.1 8B2026.0620.0719.63
CaliDist_verbalized (Pr.)LLM=LLAMA-3.1 8B2026.0620.1625.04
VerbalizedLLM=LLAMA-3.1 8B2026.0620.5724.98
CaliDist_verbalized (As.)LLM=LLAMA-3.1 8B2026.0620.5926.46
CaliDist_verbalized (Sa.)LLM=LLAMA-3.1 8B2026.0620.8424.16
VanillaLLM=LLAMA-3.1 8B2026.0623.1822.82
EntropyLLM=LLAMA-3.1 8B2026.0633.2228.2