Open Model Lab

Open Model Lab Reports

Reports from completed experiments. Upcoming research questions and targets live in the research plan.

Published reports

Reading guide: Open Model Lab reports follow a compact report template for eval identity, recorded results, failure audits, limitations, and claim boundaries.
published

Minimal Open-Model Eval Harness

Stage: July 2026 - Foundation + Eval Harness

Question: Can three open models be evaluated on the same small task suite with reproducible score, cost, latency, and failure-mode reporting?

Claim boundary: This report validates a small diagnostic harness. Its 25 draft tasks do not establish general model quality, a leaderboard, or statistical significance.