Third lineage for the cross-lineage comparison: gpt-oss-120b (text) and Qwen2.5-VL-72B (imaging) - #423

Merged

sebasmos merged 6 commits into

feat/text-lane-model-flagfrom

feat/local-third-lineage

Sep 7, 2026

Commits on Sep 6, 2026

Let a text-lane model be served locally instead of behind a vendor endpoint
sebasmos
committed
f151941
Run the five paper-headline MedQA arms on a locally served third lineage
sebasmos
committed
423ac8c
Finish the port of two runners that could not run for any second model
sebasmos
committed
e46c361
Give the referee self-inconsistency floor a --model flag
sebasmos
committed
3c3fae6
Run the imaging blind metric on a locally served third vision lineage
sebasmos
committed
538c925
Run every ported MedQA ablation, the channel arm, the referee floor and the live-peer board on gpt-oss
sebasmos
committed
d076c52