Share your thoughts, 1 month free Claude Pro on usSee more

Direct Assessment on Flask

0.7203Pearson Correlation Coefficient

LMUNIT LLaMA3.1-70B

Updated 1mo ago

Evaluation Results

Method	Links
LMUNIT LLaMA3.1-70B 2024.12		0.7203
LMUNIT LLaMA3.1-70B-Decomposed 2024.12		0.7203
LMUNIT LLaMA3.1-70B-Decomposed-Weighted 2024.12		0.7203
GPT-4o 2024.12		0.69
Claude-3.5 Sonnet 2024.12		0.6725
SFR-LLaMA-3.1-70B-Judge 2024.12		0.66
LMUNIT LLaMA3.1-8B 2024.12		0.6002
Prometheus-2-8x7B 2024.12		0.54
SFR-LLaMA-3.1-8B-Judge 2024.12		0.52
Prometheus-2-7B 2024.12		0.47
Prometheus-2-BGB-8x7B 2024.12		0.31
Llama-3-OffsetBias-8B 2024.12		0.29