← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonaisa-group/PostTrainBench

PostTrainBench

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

71.0/100
★ 570Forks: 63
View on GitHub →Homepage →
Loading report...

Similar Projects

agentic-awesome-skills

93

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,445+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

Python★ 46.9K

ctf-skills

72

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

Python★ 3.4K

awesome-llm-skills

45

A curated list of awesome LLM and AI Agent Skills, resources and tools for customising AI Agent workflows - that works with Claude Code, Codex, Gemini CLI and your custom AI Agents

Python★ 1.8K

claude-codex-settings

86

Battle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.

Python★ 1.2K
← Back to List