Cell

tower_mistral-medium-3.5_final10_reactive

Mistral-Medium-3.5 on the tower (MT0→MT23w), 3 runs. Not cited by the thesis (development or earlier run).

Outcome
Highest floor reached, per runMT4, MT4, MT8
Died0
Final HP, mean215
Seconds per model call20.9
Parse error rate11.0%
Settings
FloorTower MT0→MT23w
ModelMistral-Medium-3.5 (mistral-medium-3.5-128b, instruct)
Planningreactive
Promptengine-default-tower-basic
Temperature0
Lookahead depth2
Mechanical overrideson (logged per turn)
Engine settings (environment, 18)
THINKING_MAX_TOKENS=8192
CONVERSATION_HISTORY_TURNS=0
MOTA_OFFER_LEVELUPS=1
MOTA_TOWER_HP_FLOOR=0
MOTA_ORDER_TWO_SIDED=1
MOTA_FIGHT_KEY_FLOOD=1
MOTA_SHOP_ROUTE=1
MOTA_REMOTE_ACTIONS=1
MOTA_WAY_UP=1
MOTA_TOWER_FIDELITY=1
MOTA_PLAN_MEMORY=1
MOTA_NO_KEY_PURCHASE=1
MOTA_WAYUP_COMBINED=1
MOTA_FREE_AFFORD=1
MOTA_NPC_TRADES=1
MOTA_KEY_RESERVE=1
MOTA_AFTER_BATTLE=1
LLM_TIMEOUT=300
Runsopen one to replay it turn by turn
#outcomefinal HPHP / optturnsmodel callsreplay
1MT475–6028replay
2MT420–6029replay
3MT8549–21488replay
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>_tower_mistral-medium-3.5_final10_reactive, never over the thesis result):

python scripts/run_catalog.py --codes T10MM

Result file: results/reliability/_superseded_keyfact/tower_mistral-medium-3.5_final10_reactive.json · updated 2026-10-03