Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Gregor Betz
commited on
update about
Browse files- src/display/about.py +4 -4
src/display/about.py
CHANGED
|
@@ -55,13 +55,13 @@ Unlike these leaderboards, the `/\/` Open CoT Leaderboard assesses a model's abi
|
|
| 55 |
|
| 56 |
|
| 57 |
### π€ Open LLM Leaderboard vs. `/\/` Open CoT Leaderboard
|
| 58 |
-
* π€: Can `model` solve `task`?
|
| 59 |
`/\/`: Can `model` do CoT to improve in `task`?
|
| 60 |
-
* π€: Metric: absolute accuracy.
|
| 61 |
`/\/`: Metric: relative accuracy gain.
|
| 62 |
-
* π€: Measures `task` performance.
|
| 63 |
`/\/`: Measures ability to reason (about `task`).
|
| 64 |
-
* π€: Covers broad spectrum of `tasks`.
|
| 65 |
`/\/`: Focuses on critical thinking `tasks`.
|
| 66 |
|
| 67 |
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### π€ Open LLM Leaderboard vs. `/\/` Open CoT Leaderboard
|
| 58 |
+
* π€: Can `model` solve `task`?
|
| 59 |
`/\/`: Can `model` do CoT to improve in `task`?
|
| 60 |
+
* π€: Metric: absolute accuracy.
|
| 61 |
`/\/`: Metric: relative accuracy gain.
|
| 62 |
+
* π€: Measures `task` performance.
|
| 63 |
`/\/`: Measures ability to reason (about `task`).
|
| 64 |
+
* π€: Covers broad spectrum of `tasks`.
|
| 65 |
`/\/`: Focuses on critical thinking `tasks`.
|
| 66 |
|
| 67 |
|