Skip to content

Benchmark

DevOps-Eval ToolLearning fccr

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

86%
Mean
98.4%
Median
17.7%
Std dev
61%
10th percentile
98.8%
90th percentile
61%
Min
61%98.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1codellama-7bdataset: fc_data· Codefuse DevOps-Eval data docs98.8%
2Qwen-14B-Chatdataset: fc_data· Codefuse DevOps-Eval data docs98.4%
3Qwen-14B-Chatdataset: luban· Codefuse DevOps-Eval data docs61%

Data credits: Codefuse DevOps-Eval. Copyright 2023 Ant Group. Licensed under the Apache License, Version 2.0. Historical 2023 snapshot. (Apache-2.0 licence)