← older: fast__qwen3.6-27b__20260706-132725all runs · task boardnewer: fast__qwen3.6-27b__20260706-175057 →

fastqwen3.6-35b-a3b20260706-171844

No notes for this run yet. Add runs/fast__qwen3.6-35b-a3b__20260706-171844/NOTES.md — what was run & what changed, results, interpretation, next steps — and it will render here.

Run details

modelllama-local/qwen3.6-35b-a3bagentharnesses.plan_pi:PlanPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials9 of 9 — 5 pass · 4 failmean reward0.56tokens (job total)1,811,231 in / 102,185 outstarted / finished2026-07-06T17:18 / 2026-07-06T17:50wall clock31m22s

Tasks

cancel-async-tasks — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	2m26s	1m29s	142980/13885	long reasoning (28,230 chars)	🔍 view

filter-js-from-html — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	4m54s	1m59s	318580/18911	long reasoning (28,246 chars)	🔍 view

fix-git — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	48s	11s	34913/1451	—	🔍 view

nginx-request-logging — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	59s	20s	76540/3100	—	🔍 view

openssl-selfsigned-cert — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	55s	19s	43787/2807	—	🔍 view

query-optimize — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	12m33s	5m57s	62572/3904	—	🔍 view

regex-log — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	4m53s	4m08s	299770/42206	long reasoning (19,601 chars) ×3	🔍 view

sanitize-git-repo — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	2m15s	1m38s	744079/7554	—	🔍 view

sparql-university — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	1m34s	49s	88010/8367	long reasoning (16,766 chars)	🔍 view