Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sensory-motor control on CartPole *2
Loading...
9.8
Reward (First Iter, Worst)
gpt-oss:120b
8.656
8.953
9.25
9.547
Jun 5, 2025
Reward (First Iter, Worst)
Reward (First Iter, Best)
Reward (First Iter, Avg)
Reward (Best Iter, Worst)
Reward (Best Iter, Best)
Reward (Best Iter, Avg)
Updated 4d ago
Evaluation Results
Method
Method
Links
Reward (First Iter, Worst)
Reward (First Iter, Best)
Reward (First Iter, Avg)
Reward (Best Iter, Worst)
Reward (Best Iter, Best)
Reward (Best Iter, Avg)
gpt-oss:120b
Temperature=optimal
2025.06
9.8
486.1
245.99
500
500
500
deepseek-r1:70b
Temperature=optimal
2025.06
9.6
40.15
18.57
376.65
500
472.46
mistral-large:123b
Temperature=optimal
2025.06
9
190.8
41.54
124.95
500
415.19
llama3.3:70b
Temperature=optimal
2025.06
8.8
315.05
71.24
470.3
500
495.8
qwen2.5:72b
Temperature=optimal
2025.06
8.7
49.85
18.31
500
500
500
Feedback
Search any
task
Search any
task