Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Next State Prediction on Atari Alien ALE (online)
Loading...
79
Chosen-Action NSP Accuracy
Mind-Studio
-3.16
18.17
39.5
60.83
Jun 14, 2026
Chosen-Action NSP Accuracy
Branch NSP Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Chosen-Action NSP Accuracy
Branch NSP Accuracy
Mind-Studio
Planner=DeepSeek-V4-Fl...
2026.06
79
49
Mind-Studio
Planner=Claude-4-Sonne...
2026.06
55
38
Mind-Studio
Planner=Qwen3-Coder-48...
2026.06
50
38
PoE-World
Planner=Qwen3-Coder-48...
2026.06
48
28
Mind-Studio
Planner=Gemini-2.5-Fla...
2026.06
26
24
Mind-Studio
Planner=Llama-4-Scout-...
2026.06
24
20
LLM-as-WM
Planner=Qwen3-Coder-48...
2026.06
0
8
Feedback
Search any
task
Search any
task