← older: fast2__qwen3.6-27b__20260707-102314all runs · task boardnewer: fast2__qwen3.6-27b__20260707-121846 →

fast2qwen3.6-35b-a3b20260707-111415

No notes for this run yet. Add runs/fast2__qwen3.6-35b-a3b__20260707-111415/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 ×2.0trials6 of 6 — 2 pass · 4 failmean reward0.33tokens (job total)21,987,284 in / 225,710 outstarted / finished2026-07-07T11:14 / 2026-07-07T12:02wall clock47m50s

Tasks

financial-document-processor — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	5m47s	4m59s	853131/20204	—	🔍 view

fix-ocaml-gc — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	22m13s	20m00s	15095861/116339	fast-timeout cut at 20mlong reasoning (13,901 chars) ×10	🔍 view

git-multibranch — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	2m27s	1m43s	856966/14513	—	🔍 view

headless-terminal — 1/1 passed

#	result	total	agent	in/out tok	flags
1	PASS	2m26s	1m26s	85066/7543	—	🔍 view

mailman — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	11m48s	10m00s	4821703/58607	fast-timeout cut at 10mlong reasoning (15,091 chars) ×3	🔍 view

reshard-c4-data — 0/1 passed

#	result	total	agent	in/out tok	flags
1	FAIL	3m06s	1m27s	274557/8504	claimed success but the verifier did NOT pass (heuristic)	🔍 view