Model card
CodeT5+.
Salesforceopen-sourceUnknown paramsT5-based encoder-decoder
Open code LLM family (220M-16B). Strong on code summarization and translation. May 2023.
§ 01 · Benchmarks
Every benchmark CodeT5+ has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Bugs2Fix | Computer Code · Bug Detection | accuracy | 68.2% | #4 | 2023-05-13 | source ↗ |
| 02 | CodeSearchNet | Computer Vision · Optical Character Recognition | bleu-4 | 20.0% | #5 | 2023-05-13 | source ↗ |
| 03 | TransCoder (GeeksForGeeks) | Computer Code · Code Translation | computational-accuracy | 72.1% | #6 | 2023-05-13 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where CodeT5+ actually performs.
§ 03 · Papers
1 paper with results for CodeT5+.
- 2023-05-13· Computer Code· 3 results
CodeT5+: Open Code Large Language Models for Code Understanding and Generation
§ 04 · Related models
Other Salesforce models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.