PostTrainBench

About PostTrainBench

PostTrainBench: Can LLM Agents Automate LLM Post-Training? We introduce PostTrainBench, a benchmark that measures the ability of CLI agents to post-train pre-trained large language models (LLMs). In PostTrainBench, the agent's task is to improve the performance of a base LLM on a given benchmark. The agent is given access to an evaluation script and 10 hours on an H100 GPU. Performance is measured by the benchmark score of the post-trained LLM. This setup naturally evaluates an agent's ability to conduct AI R&D.

ai-research-automation ai-safety claude-code codex-cli gemini-cli post-training

Quick Facts

Stars	425
Forks	55
Language	Python
Category	Codex Skill
License	MIT
Quality Score	67.4302057640871/100
Open Issues	16
Last Updated	2026-07-08
Created	2025-11-28
Platforms	claude-code, cli, codex, gemini, python
Est. Tokens	~16k

Compatible Skills

These tools work well together with PostTrainBench for enhanced workflows:

claude-scholar — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (54%)
renderdoc-skill — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (53%)
talkito — semantic(0.22)+complementary+same_lang+similar_pop+shared_platform (53%)
claude-codex-settings — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (52%)
af-deep-research — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (51%)

More Codex Skill Tools

Explore other popular codex skill tools:

openclaw ⭐ 382.2k
hermes-agent ⭐ 211.4k
ui-ux-pro-max-skill ⭐ 101.6k
graphify ⭐ 80.2k
graphify ⭐ 77.1k
open-design ⭐ 76.2k
agent-skills ⭐ 71.4k
career-ops ⭐ 59.1k
taste-skill ⭐ 56.5k
system_prompts_leaks ⭐ 53.8k

View all Codex Skill tools →

Popular Python Agent Tools

hermes-agent ⭐ 211.4k · Codex Skill
AutoGPT ⭐ 185.4k · Agent Tool
skills ⭐ 157.3k · Claude Skill
langflow ⭐ 151.4k · Agent Tool
open-webui ⭐ 143.9k · MCP Server

Frequently Asked Questions

What is PostTrainBench?

PostTrainBench is Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours. It is categorized as a Codex Skill with 425 GitHub stars.

What programming language is PostTrainBench written in?

PostTrainBench is primarily written in Python. It covers topics such as ai-research-automation, ai-safety, claude-code.

How do I install or use PostTrainBench?

You can find installation instructions and usage details in the PostTrainBench GitHub repository at github.com/aisa-group/PostTrainBench. The project has 425 stars and 55 forks, indicating an active community.

What license does PostTrainBench use?

PostTrainBench is released under the MIT license, making it free to use and modify according to the license terms.

View on GitHub → Browse Codex Skill tools