simple_qwen3.5-397b_basic_multistep5
Qwen3.5-397B on the simple floor, 5 episodes. Not cited by the thesis (development or earlier run).
| Wins (boss defeated, alive) | 0/5 [0.00, 0.43] |
| Final HP / exact optimum, mean over wins | – |
| Died | 3 |
| Final HP, mean | 159 |
| Seconds per model call | 154.0 |
| Parse error rate | 43.6% |
| Floor | Simple floor |
| Model | Qwen3.5-397B (qwen3.5-397b-a17b, thinking) |
| Planning | multistep-5 |
| Prompt | engine-default-floor-basic |
| Temperature | 0 |
| Lookahead depth | 3 |
| Mechanical overrides | on (logged per turn) |
Engine settings (environment, 1)
THINKING_MAX_TOKENS=32768
| # | outcome | final HP | HP / opt | steps | model calls | replay |
|---|---|---|---|---|---|---|
| 1 | died | -1 | – | 18 | 7 | log not stored |
| 2 | not won | 517 | – | 36 | 14 | log not stored |
| 3 | died | -1 | – | 15 | 5 | log not stored |
| 4 | not won | 283 | – | 28 | 10 | log not stored |
| 5 | died | -1 | – | 11 | 3 | log not stored |
This cell has no entry in mt-ai-lab's re-run registry; its settings above and the result file describe how it was run.
Result file: results/reliability/simple_qwen3.5-397b_basic_multistep5.json · updated 2026-09-25