Update README.md
Browse files
README.md
CHANGED
|
@@ -57,12 +57,12 @@ The model uses a Generative pre-trained transformer architecture.
|
|
| 57 |
|
| 58 |
## Evaluation Results
|
| 59 |
|
| 60 |
-
The model was evaluated on the **ARC-Easy** benchmark (test split).
|
| 61 |
|
| 62 |
| Dataset | Split | Metric | Value |
|
| 63 |
|----------|-------|----------|---------|
|
| 64 |
| ARC-Easy | test | Accuracy | 17.85% |
|
| 65 |
-
|
| 66 |
|
| 67 |
## Notes
|
| 68 |
|
|
|
|
| 57 |
|
| 58 |
## Evaluation Results
|
| 59 |
|
| 60 |
+
The model was evaluated on the **ARC-Easy** and **AaI-sbench** benchmark (test split).
|
| 61 |
|
| 62 |
| Dataset | Split | Metric | Value |
|
| 63 |
|----------|-------|----------|---------|
|
| 64 |
| ARC-Easy | test | Accuracy | 17.85% |
|
| 65 |
+
AaI-sbench| test | Accuracy | 60.00%
|
| 66 |
|
| 67 |
## Notes
|
| 68 |
|