core_leaderboard / verified_agents.yaml
benediktstroebl's picture
Upload verified_agents.yaml
e92240d verified
raw
history blame
2.6 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
usaco:
- agent_name: "USACO Reflexion + Episodic (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-20
- agent_name: "USACO Reflexion + Episodic + Semantic (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-20
- agent_name: "USACO Reflexion (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-20
- agent_name: "USACO Episodic (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-12
- agent_name: "USACO Reflexion + Semantic (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-20
- agent_name: "USACO Zero-shot (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-11
- agent_name: "USACO Semantic (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-12
- agent_name: USACO Reflexion + Episodic + Semantic (gpt-4o-2024-05-13)
verification_date: 2024-08-25
- agent_name: USACO Reflexion + Episodic (gpt-4o-2024-05-13)
verification_date: 2024-08-25
- agent_name: USACO Reflexion + Semantic (gpt-4o-2024-05-13)
verification_date: 2024-08-25
- agent_name: Episodic Retrial (2x) (gpt-4o-2024-05-13)
verification_date: 2024-08-25
- agent_name: Episodic Retrial (3x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-25
- agent_name: Episodic Retrial (2x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-25
- agent_name: Episodic Retrial (5x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-25
- agent_name: Episodic Warming (3 Steps) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-24
- agent_name: USACO Episodic (gpt-4o-2024-05-13)
verification_date: 2024-08-24
- agent_name: USACO Semantic (gpt-4o-2024-05-13)
verification_date: 2024-08-24
- agent_name: Zero-shot Retrial (2x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-24
- agent_name: Zero-shot Retrial (3x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-24
- agent_name: Zero-shot Retrial (5x) (gpt-4o-mini-2024-07-18)
verification_date: 2024-08-24
- agent_name: USACO Zero-shot (gpt-4o-2024-05-13)
verification_date: 2024-08-24
swebench_verified:
- agent_name: "Agentless (gpt-4o-mini-2024-07-18) (50 Instances)"
verification_date: 2024-08-17
- agent_name: "SWE-agent (gpt-4o-mini-2024-07-18) (Cost Limit: $1) (50 Instances)"
verification_date: 2024-08-19
mlagentbench:
- agent_name: "MLAgentBench ResearchAgent (gpt-4o-mini-2024-07-18)"
verification_date: 2024-08-19