Grok Build marginal-compute SWE-bench study
Forked-trajectory experiments measuring when escalating a Grok Build run to a larger model helps on SWE-bench Verified.
SafeScan verdict · score 69/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 94
- Findings
- 0
- Scanned
- 2026-11-01
Badges are rule-based checks, not guarantees: Safe means our rules found no obvious threat in the code we could read. Review code before installing.
Botlens score · 8 factors
69/100
Each factor is 0, ½ or 1, computed only from catalog fields (scan result, coverage, findings, script files, commit/SHA, author, last seen, install link). A heuristic summary, not a guarantee.
| Scan verdict | 1/1 | Safe | |
|---|---|---|---|
| Code coverage | 1/1 | full | |
| Rule findings | 1/1 | 0 matched | |
| No executable scripts | 0/1 | 18 script file(s) of 94 | |
| Pinned source | 1/1 | commit/SHA-256 recorded | |
| Named author | 0/1 | unknown | |
| Recently seen | 1/1 | last seen 2026-10-30 | |
| Install path | 0.5/1 | source URL only |
Scan details
- Findings
- No rule matched.
- Content SHA-256
- 61214e53d2294ef2…
- Commit
- 7a68f91cae
- Files
- .gitignore
README.md
plots/dial.py
plots/marginal.py
plots/static.py
plots/static_models.py
+88
About
- Author
- RyanJunejo ↗
- Listed on
- github:RongleCat/awesome-grok-bot ↗
- Category (approx.)
- research
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗