Model comparison
lagessiehcs/ppo-LunarLander-v2 vs Gemini 2.5 Pro
Capability radar, value bars, and side-by-side posture.
lagessiehcs/ppo-LunarLander-v2
Not scored
value score
Gemini 2.5 Pro
93
value score
lagessiehcs/ppo-LunarLander-v2 ctx
—
Gemini 2.5 Pro ctx
1.0M
Capability radar
Value · context · multimodal · openness · speed posture
Value head-to-head
- Gemini 2.5 Pro93
Attribute tape
| Field | lagessiehcs/ppo-LunarLander-v2 | Gemini 2.5 Pro |
|---|---|---|
| Developer | Safe Superintelligence | Google DeepMind |
| Context | — | 1.0M |
| Modalities | Text, Code, Image, Audio, Video | |
| Openness | — | Proprietary Model |
| Speed | — | — |
| Price | — | $1.25/1M in · $10/1M out |
| Value score | — | 93 |
| Summary | A PPO-trained reinforcement learning policy for the LunarLander-v2 benchmark environment, where a neural-network agent learns to control a lunar lander's thrusters for safe landing. Trained with Stable-Baselines3 and hosted as a personal model artifact on the Hugging Face Hub. | Google frontier multimodal model. |