Our new X account is live! Follow @wizwand_team for updates

Grid-world Navigation on FrozenLake Explicit Structural Drift II

83.7Success Rate (Source)

Llama3.3-70B

Updated 4d ago

Evaluation Results

Method	Links
Llama3.3-70B 2026.01		83.7	0	-
Llama3.3-70B + GLOVE 2026.01		82.5	73.8	73.8
Qwen3-30B 2026.01		80	13.8	-
Qwen3-30B + GLOVE 2026.01		80	75	61.2
Qwen2.5-7B + GLOVE 2026.01		78.8	68.8	68.8
GPT-4o + GLOVE 2026.01		77.5	76.2	65
Grok-3 + GLOVE 2026.01		75	71.2	60
DeepSeek-V3.2 + GLOVE 2026.01		68.8	70	70
Grok-3 2026.01		60	11.2	-
Llama3.1-8B + GLOVE 2026.01		36.2	67.5	66.3
Qwen2.5-7B 2026.01		6.2	0	-
GPT-4o 2026.01		3.8	11.2	-
Llama3.1-8B 2026.01		0	1.2	-
DeepSeek-V3.2 2026.01		0	0	-