Comparison
PostTrainBench vs Learn Claude Code
Learn Claude Code has more GitHub stars (78,599 vs 594). PostTrainBench was updated more recently (last commit 1w ago). Data comes straight from GitHub and refreshes daily.
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
$
git clone https://github.com/aisa-group/PostTrainBenchLearn Claude Code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
$
git clone https://github.com/shareAI-lab/learn-claude-code| Metric | PostTrainBench | Learn Claude Code |
|---|---|---|
| Type | Plugin | Plugin |
| GitHub stars | 594 | 78,599 |
| Stars, last 7 days | n/a | n/a |
| Forks | 68 | 12,584 |
| Upvotes | 0 | 0 |
| Language | Python | Python |
| License | MIT | MIT |
| Last commit | 1w ago | 2w ago |
| Created | Nov 2025 | Jun 2025 |
| Categories | AI & LLM tooling | AI & LLM tooling |