MBPP
Basic Python problems; saturated legacy metric
codingsaturated
Definition
- Version
- not in the notes
- Category
- coding
- Maintainer
- not in the notes
- Status
- saturated
- Home page
- not in the notes
Sources
- ByteDance-Seed/Seed-Coder-8B-Instruct , Hugging Face huggingface.co https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct
Scores at a Glance
Score in %
Higher is better for this unit.
1
Seed-Coder-8B-InstructByteDance
Qwen1.5-72BAlibaba (Qwen)
Seed-Coder-8B-InstructByteDance85.2 %
vendor-reported2Qwen1.5-72BAlibaba (Qwen)53.4 %
vendor-reported0255075100
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.
Scores
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| Seed-Coder-8B-Instruct | 85.2 % | vendor-reported | – | – | – | huggingface.co |
| Qwen1.5-72B | 53.4 % | vendor-reported | – | – | 4 Feb 2024 | qwenlm.github.io |
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "MBPP", https://aurion.semai.id/benchmarks/mbpp/, records of October 2026.