Cell · cited by the thesis

gen02_qwen3.5-397b_final2

Qwen3.5-397B on gen02, 3 episodes. Cited by the thesis in:

Outcome
Wins (boss defeated, alive)3/3 [0.44, 1.00]
Final HP / exact optimum, mean over wins100%
Died0
Final HP, mean232
Seconds per model call54.8
Parse error rate0.0%
Settings
Floorgen02
ModelQwen3.5-397B (qwen3.5-397b-a17b, thinking)
Planningreactive
Promptengine-default-floor-basic
Temperature0
Lookahead depth3
Mechanical overrideson (logged per turn)
Engine settings (environment, 4)
THINKING_MAX_TOKENS=32768
CONVERSATION_HISTORY_TURNS=0
MOTA_ORDER_TWO_SIDED=1
MOTA_FIGHT_KEY_FLOOD=1
Episodesopen one to replay it turn by turn
#outcomefinal HPHP / optstepsmodel callsreplay
1won232100%217replay
2won232100%217replay
3won232100%217replay
Re-run this cell

In a checkout of mt-ai-lab with an API key set (the result goes to a new file rerun_<time>_gen02_qwen3.5-397b_final2, never over the thesis result):

python scripts/run_catalog.py --codes GEN2

Result file: results/reliability/gen02_qwen3.5-397b_final2.json · updated 2026-09-28