core_leaderboard / verified_agents.yaml
Zachary Siegel
verify the agents
abf78cc
raw
history blame
1.13 kB
# This file contains information about verified agent results for different benchmarks.
# Format:
# benchmark_name:
# - agent_name: "Name of the agent"
# verification_date: YYYY-MM-DD
corebench_easy:
- agent_name: "AutoGPT (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "AutoGPT (GPT-4o-mini)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o-mini)"
verification_date: 2024-09-28
corebench_medium:
- agent_name: "AutoGPT (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "AutoGPT (GPT-4o-mini)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o-mini)"
verification_date: 2024-09-28
corebench_hard:
- agent_name: "AutoGPT (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "AutoGPT (GPT-4o-mini)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o)"
verification_date: 2024-09-28
- agent_name: "CORE-Agent (GPT-4o-mini)"
verification_date: 2024-09-28