# Archived benchmark results

Runs set aside on 2026-09-27. They are kept as the record of how the local
model choice was made, but the report no longer reads them: `benchmark.py
report` only looks at `bench/results/*.jsonl`, not this folder.

- **2026-09-25, `local-coder` and `local-fast`:** qwen3-14b and qwen3-8b-awq
  on the original RTX 4070 box. Both models were later dropped.
- **2026-09-27, seven newer models and `local-fast` on the RTX 4090 (PR #49):**
  every newer model passed all four original tasks 20/20, which is why four
  harder tasks were added. Pass rates are still valid; timings are not
  comparable with later runs, which were made under a 320 W power cap rather
  than 450 W or 350 W, with `max_turns` 40 rather than 24.

Later results were made after the fixes in PRs #50–#52: rate-limit waits
recorded, one assistant message per turn, a 600 s request timeout, and tuning
kept apart in the report.