agent-benchmark

Here are 5 public repositories matching this topic...

likecheng110 / osac-bench

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

multi-agent-systems system-administration research-only agent-collaboration os-agent stateful-agents agent-benchmark tool-using-agents deterministic-evaluation linux-operations evidence-grounding memory-evaluation continuous-tasks

Updated Jul 29, 2026
JavaScript

ahmetarifoz / agent-deathtrap-models

Star

Agent-LLM Benchmark Model Results

benchmark open-data gemini gpt ai-safety ai-agents claude tool-use large-language-models prompt-injection llm-evaluation agentic-ai llm-leaderboard agent-benchmark llm-benchmark

Updated Jul 14, 2026
JavaScript

Dmatut7 / shoppay-audit-benchmark

Star

AI business-logic audit benchmark for Codex-style coding agents

nodejs open-source benchmark payments business-logic software-testing codex ai-agent llm-evaluation coding-agents ai-audit agent-benchmark business-logic-bugs

Updated Jun 5, 2026
JavaScript

L-X-J / tank-battle-agent-benchmark

Star

用同一套提示词评测多模型 Agent 从零实现完整可玩游戏的能力：固定技术栈、固定评分标准、按模型归档对比。| A standardized prompt for benchmarking LLM agents on building a complete game from scratch — fixed tech stack, fixed rubric, per-model results.

nodejs benchmark canvas game-development web-audio code-generation tank-battle llm-agents agent-benchmark agent-benchmarks

Updated Aug 14, 2026
JavaScript

aLexzzz430 / hundred-winters

Star

A long-horizon benchmark for agents that must keep a civilization alive through 100 winters.

codex long-horizon agent-benchmark gpt-5-6 openai-build-week

Updated Jul 17, 2026
JavaScript

Add this topic to your repo

To associate your repository with the agent-benchmark topic, visit your repo's landing page and select "manage topics."

Learn more