agent-benchmark 开源项目推荐（109 个）

ktwu01 /benchmark-radar

Track 42,331+ AI benchmark, eval, dataset, and data-quality records from 40 public sources, with linked evidence and daily updates.

hidai25 /eval-view

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

js-lee-AI /awesome-llm-agent-papers

LLM agents: curated papers on planning, memory, tool use, multi-agent systems, evaluation, and safety.

HuangShengZeBlueSky /dsh-harness-evolution

Evolved DSH plugin harnesses for five agent benchmarks, with versioned artifacts, evolution curves and Life-Harness comparisons

agentvitals /checkup

AgentVitals Checkup (/checkup) — an AI agent skill that gives your agent a professional health checkup: dual-axis Stability + Welfare scoring, a personality-style title, and a public cross-platform leaderboard. One-line install for Claude Code / OpenClaw / Codex / Coze. Bilingual EN/ZH.

Cre4T3Tiv3 /ai-agents-reality-check

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.

OpenBMB /EC2-Bench

EC2-Bench (EC²-Bench): benchmark for edge-cloud collaboration in long-horizon LLM agents — task performance, resource usage & privacy exposure. arXiv 2610.17816

collinear-ai /tau-trait

TraitBasis applied to TauBench

mll-lab-nu /BAGEN

BAGEN (Budget-Aware Agent): benchmark and training code for budget-aware LLM agents that estimate token, time, and money cost mid-task.

likecheng110 /osac-bench

Research benchmark for evidence-grounded OS-agent collaboration, continuous state diagnosis, scoped memory reuse, and stale-state rejection.

wenhuahuo /BABY

BABY - Build Agent Benchmarks for Yourself

NoesisVision /nasde-toolkit

CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

hanxiao /jy-crpg-bench

A long-horizon CRPG benchmark for frontier agents. Raw 320x200 frames, Traditional Chinese, isometric navigation, twelve books to find.

edholofy /dojo.md

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.

MSKazemi /aobench

Role-aware, permission-enforced benchmark for LLM agents that operate HPC systems — SLURM, telemetry, RBAC, docs, facility. A policy violation hard-fails the task. 88 tasks (10 categories x 5 roles), 29 reproducible environments with 6 rebuilt from real Marconi100 ExaData, scored on 7 weighted dimensions.

itsjawreal /halu-core

Scores whether an autonomous AI agent actually did the work or just hallucinated its report, by checking every claim against recorded API calls. The core engine behind NoHalu.

dataanswer /awesome-agent-benchmarks

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

he-yufeng /CodeJoust

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

haoyifan /Silicon-Pantheon

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

justindobbs /Tracecore

Deterministic runtime for agent evaluation