← older: smoke__qwen3.6-35b-a3b__20260726-025257all runs · task boardnewer: smoke__qwen3.6-35b-a3b__20260726-042939 →

smokeqwen3.6-35b-a3b20260726-034536

No notes for this run yet. Add runs/smoke__qwen3.6-35b-a3b__20260726-034536/NOTES.md — what was run & what changed, results, interpretation, next steps — and it will render here.

Run details

modelllama-local/qwen3.6-35b-a3bagentharnesses.minimal_pi:MinimalPithinkingonreasoning budgetdirect (server/none)* — see journal for the authoritative mechanismmaxTokens / contextWindow65536 / 196608agent timeout ×2.0trials9 of 9 — 5 pass · 4 failmean reward0.56tokens (job total)7,285,830 in / 119,769 outstarted / finished2026-07-26T03:45 / 2026-07-26T04:26wall clock40m53s

Tasks

cobol-modernization — 2/3 passed

#	result	total	agent	in/out tok	flags
1	FAIL	20m35s	20m00s	1006595/34462	fast-timeout cut at 20m	🔍 view
2	PASS	3m14s	2m40s	863819/25746	long reasoning (22,869 chars) ×2	🔍 view
3	PASS	2m04s	1m30s	393195/15312	—	🔍 view

crack-7z-hash — 3/3 passed

#	result	total	agent	in/out tok	flags
1	PASS	2m43s	2m04s	115312/2743	—	🔍 view
2	PASS	2m40s	2m01s	86687/2189	—	🔍 view
3	PASS	2m40s	2m02s	376654/4133	a bash command timed out	🔍 view

sanitize-git-repo — 0/3 passed

#	result	total	agent	in/out tok	flags
1	FAIL	1m56s	1m22s	1037137/9185	—	🔍 view
2	FAIL	1m43s	1m09s	908993/8538	—	🔍 view
3	FAIL	3m13s	2m40s	2497438/17461	—	🔍 view