Hugging Face's logo

Spaces:
logikon
/
open_cot_leaderboard
Running on CPU Upgrade

App Files Community
2
Gregor Betz commited on
Commit
e6eced8
·
unverified ·
1 Parent(s): 14dbcf4

update models

Browse files
Files changed (1) hide show
  1. src/display/about.py +1 -1
src/display/about.py CHANGED
@@ -33,7 +33,7 @@ The Open CoT Leaderboard tracks the reasoning skills of LLMs, measured as their
33
 
34
  The leaderboard reports **accuracy gains** achieved by using [chain-of-thought](https://logikon.ai/docs/delib_prompting) (CoT), i.e.: _accuracy gain Δ_ = _accuracy with CoT_ — _accuracy w/o CoT_.
35
 
36
- See the "About" tab for more details and motivation.
37
  """
38
 
39
  # Which evaluations are you running? how can people reproduce what you have?
 
33
 
34
  The leaderboard reports **accuracy gains** achieved by using [chain-of-thought](https://logikon.ai/docs/delib_prompting) (CoT), i.e.: _accuracy gain Δ_ = _accuracy with CoT_ — _accuracy w/o CoT_.
35
 
36
+ Detailed model-specific results can be explored with the [Open CoT Dashboard](https://huggingface.co/spaces/cot-leaderboard/open-cot-dashboard). See the "About" tab for background infos and motivation.
37
  """
38
 
39
  # Which evaluations are you running? how can people reproduce what you have?