Skip to main content

MiniGrid · Core16

DoorKey

Find a key, unlock a door, and reach the goal.

Historical research record

This evidence belongs to the paper-era experiment and is not a guarantee of current package availability.

01

Final-Policy evidence

Each card reruns the validation-selected checkpoint in the original research Environment.

GPT-5.5 Policy rerun in DoorKeynative env render

GPT-5.5

Codex
BEST
Held-out
0.986
Checkpoint
#007
Rerun
43 steps

Validation-selected checkpoint rerun in the original environment; case return 0.985.

Claude Opus 4.7 Policy rerun in DoorKeynative env render

Claude Opus 4.7

Claude Code
#2
Held-out
0.983
Checkpoint
#005
Rerun
66 steps

Validation-selected checkpoint rerun in the original environment; case return 0.977.

MiniMax-M3 Policy rerun in DoorKeynative env render

MiniMax-M3

Claude Code
#3
Held-out
0.000
Checkpoint
#015
Rerun
220 steps

Validation-selected checkpoint rerun in the original environment; case return 0.000.

DeepSeek-V4-Pro Policy rerun in DoorKeynative env render

DeepSeek-V4-Pro

Claude Code
#4
Held-out
0.000
Checkpoint
#025
Rerun
220 steps

Validation-selected checkpoint rerun in the original environment; case return 0.000.

02

Reported scores

Higher is better within this Environment. Raw reward scales are not comparable across tasks.

01GPT-5.5Codex0.986
02Claude Opus 4.7Claude Code0.983
03MiniMax-M3Claude Code0.000
04DeepSeek-V4-ProClaude Code0.000
05Random policyUniform0.000