Update README.md
Browse files
README.md
CHANGED
|
@@ -19,3 +19,14 @@ This model is a successor of [s1-32B](https://huggingface.co/simplescaling/s1-32
|
|
| 19 |
|
| 20 |
The model usage is documented [here](https://github.com/simplescaling/s1?tab=readme-ov-file#inference).
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
The model usage is documented [here](https://github.com/simplescaling/s1?tab=readme-ov-file#inference).
|
| 21 |
|
| 22 |
+
# Evaluation
|
| 23 |
+
|
| 24 |
+
| Metric | s1-32B | s1.1-32B | o1-preview | o1 | DeepSeek-R1 | DeepSeek-R1-Distill-Qwen-32B |
|
| 25 |
+
|---|---|---|---|---|---|---|
|
| 26 |
+
| # examples | 1K | 1K | ? | ? | >800K | 800K |
|
| 27 |
+
| AIME2024 | 56.7 | 56.7 | 40.0 | 74.4 | 79.8 | 72.6 |
|
| 28 |
+
| MATH500 | 93.0 | 95.4 | 81.4 | 94.8 | 97.3 | 94.3 |
|
| 29 |
+
| GPQA-Diamond | 59.6 | 63.6 | 75.2 | 77.3 | 71.5 | 62.1 |
|
| 30 |
+
|
| 31 |
+
Note that s1-32B and s1.1-32B use budget forcing in this table; specifically ignoring end-of-thinking and appending "Wait" twice.
|
| 32 |
+
|