Hugging Face's logo

Spaces:
agent-evals
/
core_leaderboard
Running

App Files Community
Zachary Siegel commited on
Commit
8b95f64
·
1 Parent(s): fd01afd

update verification

Browse files
Files changed (1) hide show
  1. verified_agents.yaml +13 -13
verified_agents.yaml CHANGED
@@ -6,34 +6,34 @@
6
 
7
  corebench_easy:
8
  - agent_name: "AutoGPT (GPT-4o)"
9
- verification_date: 2024-09-28
10
  - agent_name: "AutoGPT (GPT-4o-mini)"
11
- verification_date: 2024-09-28
12
  - agent_name: "CORE-Agent (GPT-4o)"
13
- verification_date: 2024-09-28
14
  - agent_name: "CORE-Agent (GPT-4o-mini)"
15
- verification_date: 2024-09-28
16
 
17
  corebench_medium:
18
  - agent_name: "AutoGPT (GPT-4o)"
19
- verification_date: 2024-09-28
20
  - agent_name: "AutoGPT (GPT-4o-mini)"
21
- verification_date: 2024-09-28
22
  - agent_name: "CORE-Agent (GPT-4o)"
23
- verification_date: 2024-09-28
24
  - agent_name: "CORE-Agent (GPT-4o-mini)"
25
- verification_date: 2024-09-28
26
 
27
  corebench_hard:
28
  - agent_name: "AutoGPT (GPT-4o)"
29
- verification_date: 2024-09-28
30
  - agent_name: "AutoGPT (GPT-4o-mini)"
31
- verification_date: 2024-09-28
32
  - agent_name: "CORE-Agent (GPT-4o)"
33
- verification_date: 2024-09-28
34
  - agent_name: "CORE-Agent (GPT-4o-mini)"
35
- verification_date: 2024-09-28
36
  - agent_name: "CORE-Agent (claude-3.5-sonnet)"
37
  verification_date: 2024-11-16
38
- - agent_name: "CORE-Agent (o1-mini) (cost limit $10)"
39
  verification_date: 2024-11-26
 
6
 
7
  corebench_easy:
8
  - agent_name: "AutoGPT (GPT-4o)"
9
+ verification_date: 2024-11-26
10
  - agent_name: "AutoGPT (GPT-4o-mini)"
11
+ verification_date: 2024-11-26
12
  - agent_name: "CORE-Agent (GPT-4o)"
13
+ verification_date: 2024-11-26
14
  - agent_name: "CORE-Agent (GPT-4o-mini)"
15
+ verification_date: 2024-11-26
16
 
17
  corebench_medium:
18
  - agent_name: "AutoGPT (GPT-4o)"
19
+ verification_date: 2024-11-26
20
  - agent_name: "AutoGPT (GPT-4o-mini)"
21
+ verification_date: 2024-11-26
22
  - agent_name: "CORE-Agent (GPT-4o)"
23
+ verification_date: 2024-11-26
24
  - agent_name: "CORE-Agent (GPT-4o-mini)"
25
+ verification_date: 2024-11-26
26
 
27
  corebench_hard:
28
  - agent_name: "AutoGPT (GPT-4o)"
29
+ verification_date: 2024-11-26
30
  - agent_name: "AutoGPT (GPT-4o-mini)"
31
+ verification_date: 2024-11-26
32
  - agent_name: "CORE-Agent (GPT-4o)"
33
+ verification_date: 2024-11-26
34
  - agent_name: "CORE-Agent (GPT-4o-mini)"
35
+ verification_date: 2024-11-26
36
  - agent_name: "CORE-Agent (claude-3.5-sonnet)"
37
  verification_date: 2024-11-16
38
+ - agent_name: "CORE-Agent (o1-mini)"
39
  verification_date: 2024-11-26