Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Atari Game Playing on Atari Assault ALE (online)
Loading...
84
Task Outcome Score
Mind-Studio
18.48
35.49
52.5
69.51
Jun 14, 2026
Task Outcome Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Task Outcome Score
Mind-Studio
Planner=Qwen3-Coder-48...
2026.06
84
Mind-Studio
Planner=Llama-4-Scout-...
2026.06
84
LLM-as-WM
Planner=Qwen3-Coder-48...
2026.06
63
Mind-Studio
Planner=Claude-4-Sonne...
2026.06
63
PoE-World
Planner=Qwen3-Coder-48...
2026.06
42
Mind-Studio
Planner=DeepSeek-V4-Fl...
2026.06
42
Mind-Studio
Planner=Gemini-2.5-Fla...
2026.06
42
REAL
Planner=Qwen3-Coder-48...
2026.06
21
Feedback
Search any
task
Search any
task