AI Dev Impact Lab JA
← Topics ranking · 2026-11
GITHUB TOPIC

#gaia-benchmark

GitHub repositories that have self-applied the topic "gaia-benchmark" — a creator-tagged metadata that surfaces how AI projects describe themselves.

2
tagged repos
1
top 2 stars
0
with tool sigs
2
shown

REPOS Repos for #gaia-benchmark (top 2 by stars)

paopao-13/pecs-multi-agent

PECS: 基于 LangGraph 的四角色多智能体任务求解框架(Planner/Executor/Critic/Synthesizer)。WebShop 真实环境 +25pp (25% vs 0%);GAIA 官方 53 题 26.4% vs ReAct 24.5%(McNemar 不显著)。含 AST 沙箱、50000 token 硬预算、FastAPI 限流/混沌/CI/Prometheus。

Python ★ 1 AI 100
erayozgr/final-agent

AI agent built with smolagents for the Hugging Face Agents Course final assignment. Scored 90% (18/20) on a GAIA benchmark subset using web search, Wikipedia, file parsing (Excel, Python, audio, images) and Claude Haiku.

Python ★ 0 AI 90

RELATED Other topics · full topics ranking →

#claude-code

3,787

#ai-agents

3,201

#llm

2,090

#mcp

1,866

#claude

1,854

#python

1,678

#developer-tools

1,530

#codex

1,376

#ai

1,181

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology