Sensory-motor control on CartPole
42.15Reward (First Iteration, Worst Rep)gpt-oss:120b
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| gpt-oss:120bTemperature=optimal2025.06 | 42.15 | 500 | 344.32 | 500 | 500 | 500 | |
| qwen2.5:72bTemperature=optimal2025.06 | 41.55 | 44.1 | 43.05 | 66.85 | 500 | 425.31 | |
| llama3.3:70bTemperature=optimal2025.06 | 9.2 | 172.65 | 74.45 | 352.35 | 500 | 484.46 | |
| deepseek-r1:70bTemperature=optimal2025.06 | 8.7 | 45.75 | 12.6 | 473.75 | 500 | 495.78 | |
| mistral-large:123bTemperature=optimal2025.06 | 8.6 | 8.85 | 8.78 | 52.9 | 500 | 429.5 |