direct mujoco rendererGPT-5.5
Codex- Held-out
- -37.11
- Checkpoint
- #005
- Rerun
- 100 steps
Validation-selected checkpoint rerun in the original environment; case return -38.36.
MuJoCo · Core16
Pusher
Contact manipulation that pushes an object to a goal.
Historical research record
This evidence belongs to the paper-era experiment and is not a guarantee of current package availability.
Final-Policy evidence
Each card reruns the validation-selected checkpoint in the original research Environment.
direct mujoco rendererBEST
direct mujoco rendererClaude Opus 4.7
Claude Code- Held-out
- -38.52
- Checkpoint
- #014
- Rerun
- 100 steps
Validation-selected checkpoint rerun in the original environment; case return -37.53.
direct mujoco rendererMiniMax-M3
Claude Code- Held-out
- -39.25
- Checkpoint
- #010
- Rerun
- 100 steps
Validation-selected checkpoint rerun in the original environment; case return -41.99.
direct mujoco rendererDeepSeek-V4-Pro
Claude Code- Held-out
- -54.18
- Checkpoint
- #004
- Rerun
- 100 steps
Validation-selected checkpoint rerun in the original environment; case return -55.45.
Reported scores
Higher is better within this Environment. Raw reward scales are not comparable across tasks.
01GPT-5.5Codex
-37.1102Claude Opus 4.7Claude Code
-38.5203MiniMax-M3Claude Code
-39.2504DeepSeek-V4-ProClaude Code
-54.1805Random policyUniform
-147.5