CodeLlama-13B-Python-hf Benchmark Results

CodeLlama-13B-Python-hf — benchmark results

Provider: Meta. Released 2023-08-24. Access: Open.

Unified ELO 1191 ± 19, rank #1700 of 1776 rated models, from 72 benchmark results.

Benchmark	Score	Metric	Percentile
ToolBench - Tabletop	41.53	Task Score	86
ToolBench - The Cat API	92.35	Task Score	86
ToolBench - Home Search	86	Task Score	83.7
ToolBench - Google Sheets	50.79	Task Score	81.4
ToolBench - Open Weather	93	Task Score	80.2
ToolBench Leaderboard	56.31	Average Task Score	79.1
ToolBench - VirtualHome	21.94	Task Score	76.7
ToolBench - Trip Booking	62.5	Task Score	62.8
ToolBench - WebShop Short	2.4	Task Score	62.8
MMLU-by-task - Moral Scenarios	27.15	Accuracy (%)	58.5
MMLU-by-task - High School Statistics	39.81	Accuracy (%)	54.6
MMLU-by-task - High School Physics	29.8	Accuracy (%)	46.5