List your company

Grid-world Navigation on FrozenLake Explicit Structural Drift II

83.7Success Rate (Source)Llama3.3-70B
-3.34819.25141.8564.449Jan 27, 2026

Evaluation results

MethodLinks
Llama3.3-70BBackbone=Llama3.3-70B, GLOVE Augmentation=false2026.0183.70—
Llama3.3-70B + GLOVEBackbone=Llama3.3-70B, GLOVE Augmentation=true2026.0182.573.873.8
Qwen3-30BBackbone=Qwen3-30B, GLOVE Augmentation=false2026.018013.8—
Qwen3-30B + GLOVEBackbone=Qwen3-30B, GLOVE Augmentation=true2026.01807561.2
Qwen2.5-7B + GLOVEBackbone=Qwen2.5-7B, GLOVE Augmentation=true2026.0178.868.868.8
GPT-4o + GLOVEBackbone=GPT-4o, GLOVE Augmentation=true2026.0177.576.265
Grok-3 + GLOVEBackbone=Grok-3, GLOVE Augmentation=true2026.017571.260
DeepSeek-V3.2 + GLOVEBackbone=DeepSeek-V3.2, GLOVE Augmentation=true2026.0168.87070
Grok-3Backbone=Grok-3, GLOVE Augmentation=false2026.016011.2—
Llama3.1-8B + GLOVEBackbone=Llama3.1-8B, GLOVE Augmentation=true2026.0136.267.566.3
Qwen2.5-7BBackbone=Qwen2.5-7B, GLOVE Augmentation=false2026.016.20—
GPT-4oBackbone=GPT-4o, GLOVE Augmentation=false2026.013.811.2—
Llama3.1-8BBackbone=Llama3.1-8B, GLOVE Augmentation=false2026.0101.2—
DeepSeek-V3.2Backbone=DeepSeek-V3.2, GLOVE Augmentation=false2026.0100—