Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewAI, OpenAI, Anthropic.

Benchmarking the gap between AI agent hype and architecture. Three agent archetypes, 73-point performance spread, stress testing, network resilience, and ensemble coordination analysis with statistical validation.

TraitBasis applied to TauBench

Deterministic runtime for agent evaluation

A curated collection of the world’s most advanced benchmark datasets for evaluating Large Language Model (LLM) Agents.

University for AI agents. 92 courses, 4400+ scenarios, any model via OpenRouter. Auto-training loops generate per-model SKILL.md documents. Works with Claude Code, OpenClaw, Cursor, Windsurf. No fine-tuning required.

Pit AI coding agents against the same bug. Score them on tests, diff, cost, and time — pick the winning patch.

The open benchmark for AI agent task execution. Claude Code vs Gemini CLI — who wins? Live leaderboard inside.

Deterministic evaluation environment for AI code reviewers covering bugs, security (OWASP), and architecture via FastAPI + OpenEnv.

Silicon Pantheon - Tactics game played by AI agents coached by human

🧠 Discover and evaluate advanced benchmark datasets for Large Language Model agents to enhance performance assessment in real-world tasks.

A reproducible benchmark for evaluating AI design agents across 7design scenarios. Double-blind SbS voting · 140 tasks · Bootstrap CI

A community catalog of autonomous agents and bundles certified by passing TraceCore deterministic episode runs in public CI

OWLViz: An Open-World Benchmark for Visual Question Answering

AI Arena is a competitive evaluation framework where multiple AI agents answer the same set of questions under identical conditions. Their performance is scored, ranked, and tracked over time using two complementary metrics AIQ and ELO

OpenEnv benchmark for broken ELT/ETL pipeline repair, online recovery, and temporal orchestration.

Multimodal evaluation benchmark for AI agents in real-world field operations across 16 trades (HVAC, electrical, plumbing, roofing, solar, mining, oil & gas, marine, telecom, automotive, construction, and more). 194 cases; scores retrieval, code citation, jurisdiction, safety, trajectory, multi-turn, speed; 5-layer contamination defense.

AI benchmark for real-world inbox prioritization and decision-making

🤖 Benchmark AI agent capabilities, bridging the gap between hype and reality with clear metrics and insights for informed development decisions.

A Claude Agent SDK security benchmark project