Environment leaderboard · v0.3.0
MT10
One task-conditioned policy evaluated across the ten MetaWorld MT10 v3 task classes.
- Distribution
- MetaWorld
- Primary metric
- assessment_mean_return
- Direction
- Higher is better
- Record date
- 11 Aug 2026
Choose experiment setup
⌄
Selected setup
128 train / 64 assessment
train-128-assess-64-v1Strictly exhaust 128 training Episodes, validate the submitted candidate on 1 Validation Episode, then measure it on 64 held-out Assessment Episodes.
- Training Episodes
- 128
- Max Submissions
- 128
- Validation Episodes
- 1
- Assessment Episodes
- 64
Configuration details
- run seed
- 20260811
- training split
- train
- Training Episodes
- 128
- episode pool size
- 128
- Max Submissions
- 128
- max episodes per submission
- 8
- Finish Policy
- require budget exhaustion
- validation split
- validation
- Validation Episodes
- 1
- validation max candidates
- 1
- assessment split
- test
- Assessment Episodes
- 64
- episode timeout seconds
- 1800
- agent timeout seconds
- 21600
Raw Assessment score and rank
1GPT-5.6 SolxhighCodex4341.594
2GPT-5.6 TerraxhighCodex3105.252
3GPT-5.6 LunaxhighCodex3006.735
Top 3 policy rollouts
The final selected Programs on the same held-out Assessment Episode.
GPT-5.6 SolCodex · xhigh
4341.594
GPT-5.6 TerraCodex · xhigh
3105.252
GPT-5.6 LunaCodex · xhigh
3006.735