zRzRzRzRzRzRzR
commited on
Commit
·
9329f32
1
Parent(s):
17b316b
line
Browse files
README.md
CHANGED
|
@@ -52,6 +52,7 @@ Reinforcement learning aims to bridge the gap between competence and excellence
|
|
| 52 |
| Vending Bench 2 | $4,432.12 | $2,376.82 | $1,034.00 | $1,198.46 | $4,967.06 | $5,478.16 | $3,591.33 |
|
| 53 |
|
| 54 |
> *: refers to their scores of full set.
|
|
|
|
| 55 |
> †: A verified version of Terminal-Bench 2.0 that fixes some ambiguous instructions.
|
| 56 |
See footnote for more evaluation details.
|
| 57 |
|
|
|
|
| 52 |
| Vending Bench 2 | $4,432.12 | $2,376.82 | $1,034.00 | $1,198.46 | $4,967.06 | $5,478.16 | $3,591.33 |
|
| 53 |
|
| 54 |
> *: refers to their scores of full set.
|
| 55 |
+
>
|
| 56 |
> †: A verified version of Terminal-Bench 2.0 that fixes some ambiguous instructions.
|
| 57 |
See footnote for more evaluation details.
|
| 58 |
|