Benchmark
DevOps-Eval ToolLearning aar
Scores are percentages. Higher is better.
Benchmark sourceScores from Codefuse DevOps-Eval data docs.
- Models measured
- 2
- Scores recorded
- 3
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 81.9%
- Mean
- 81.6%
- Median
- 10.3%
- Std dev
- 69.5%
- 10th percentile
- 94.7%
- 90th percentile
- 69.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | codellama-7bdataset: fc_data· Codefuse DevOps-Eval data docs | 94.7% |
| 2 | Qwen-14B-Chatdataset: fc_data· Codefuse DevOps-Eval data docs | 81.6% |
| 3 | Qwen-14B-Chatdataset: luban· Codefuse DevOps-Eval data docs | 69.5% |
Data credits: Codefuse DevOps-Eval. Copyright 2023 Ant Group. Licensed under the Apache License, Version 2.0. Historical 2023 snapshot. (Apache-2.0 licence)