pinned
Running
Agents
7
TRAIL Leaderboard
🥇
Trace Reasoning and Agentic Issue Localization Leaderboard
LLM Evaluation
Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL
Benchmarking Reward Hack Detection in Code Environments via Contrastive Analysis
Trace Reasoning and Agentic Issue Localization Leaderboard
BLUR leaderboard.
GLIDER: Grading LLM Interactions and Decisions using Explain
Evaluate answer fidelity to document