Seed Diffusion Preview
Seed Diffusion Preview.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Seed Diffusion Preview
Closed weights Small
No Epoch Capabilities Index score yet
- BigCodeBench 53.2% #4 /11
- Aider-Edit 44.4% #5 /5
- LiveCodeBench 33.7% #58 /73
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CanItEdit | 54.3% | #1 of 3 | Model card | |
| MBPP | 79.4% | #23 of 66 | Model card | |
| BigCodeBench | 53.2% | #4 of 11 | Model card | |
| HumanEval | 82.8% | #46 of 95 | Model card | |
| LiveCodeBench | 33.7% | #58 of 73 | Model card | |
| Aider-Edit | 44.4% | #5 of 5 | Model card | |
| MBXP | 72.6% | #3 of 3 | Model card | |
| NaturalCodeBench | 42.2% | #2 of 2 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it.
Capabilities
- HumanEval 82.8
- MBPP 79.4
- BigCodeBench 53.2
- LiveCodeBench 33.7
- Aider-Edit 44.4
- CanItEdit 54.3
- MBXP 72.6
- NaturalCodeBench 42.2