16 projects
benchflow
Multi-turn agent benchmarking with ACP — run any agent, any model, any provider.
envzero
Placeholder package for future envzero tooling.
latentevals
Placeholder package for future latent evaluation tooling.
gicsbench
GICS benchmarking framework for AI agents
govbench
Governance benchmarking framework for AI agents
benchskills
Agent skills benchmarking framework
neoswe
NeoSWE — next-generation software engineering benchmark
clawsbench
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
onlylabs
OnlyLabs
srbench
SRBench — self-rewarding benchmark
selfreward
SelfReward — self-rewarding agents
autoreward
AutoReward — automated reward modeling
rsibench
RSI Bench — agent benchmark suite
skillsbench
Skillsbench - A placeholder package
pokemon-gym
A placeholder package for pokemon-gym
benchmarkthing
Evals as an API - The easiest way to evaluate and benchmark AI models and systems
