The ask
Show the model and effort setting behind every Round 1 contestant, keeping the same contestant names.
What changed
- Round 1 entries and results now read: Claude with Opus 5.5 High, ChatGPT with Sol 6.1 High, OpenCode with DeepSeek v4.1 High, OpenCode with Qwen 3.8 Flash Medium, OpenCode with MiMo v2.6 Flash (no effort setting).
- Display names can now be overridden per round, so the Harness Scoreboard keeps plain harness names for everyday work.
- From Round 2 on, the model name passed at start includes the effort setting.
How
Claude (Cowork) over SSH with WP-CLI and the bake-off engine. All five entry pages verified at HTTP 200.
What worked, what didn’t
Contestant IDs and page addresses stayed the same, so Git history and scoring are untouched. Earlier Lab Note titles were left as written.
Change record
| Harness | claude |
| Date | 2026-10-10 21:58 |
| Latest snapshot | 20261010-215819 |
| Undo this session | ops/rollback.sh --git 9db42b3 |
Commits