Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,21 @@ OlympicCoder-32B is a code mode that achieves very strong performance on competi
|
|
| 25 |
|
| 26 |
## Evaluation
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
|
| 29 |
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
|
| 32 |
|
|
|
|
| 25 |
|
| 26 |
## Evaluation
|
| 27 |
|
| 28 |
+
We compare the performance of OlympicCoder models on two main benchmarks for competitive coding:
|
| 29 |
+
|
| 30 |
+
* **[IOI'2024:](https://github.com/huggingface/ioi)** 6 very challenging problems from the 2024 International Olympiad in Informatics. Models are allowed up to 50 submissions per problem.
|
| 31 |
+
* **[LiveCodeBench:](https://livecodebench.github.io)** Python programming problems source from platforms like CodeForces and LeetCoder. We use the `v4_v5` subset of [`livecodebench/code_generation_lite`](https://huggingface.co/datasets/livecodebench/code_generation_lite), which corresponds to 268 problems. We use `lighteval` to evaluate models on LiveCodeBench using the sampling parameters described [here](https://github.com/huggingface/open-r1?tab=readme-ov-file#livecodebench).
|
| 32 |
+
|
| 33 |
+
> [!NOTE]
|
| 34 |
+
> The OlympicCoder models were post-trained exclusively on C++ solutions generated by DeepSeek-R1. As a result the performance on LiveCodeBench should be considered to be partially _out-of-domain_, since this expects models to output solutions in Python.
|
| 35 |
+
|
| 36 |
+
### IOI'24
|
| 37 |
+
|
| 38 |
|
| 39 |
|
| 40 |
+
### LiveCodeBench
|
| 41 |
+
|
| 42 |
+
|
| 43 |
|
| 44 |
|
| 45 |
|