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

Agent Behavior Adaptation on BlocksWorld (BW) (test)

51Loop Ratio

Mistral-7B-Instruct

Updated 4d ago

Evaluation Results

Method	Links
Mistral-7B-Instruct 2026.02		51
Qwen3-4B-Thinking 2026.02		28.5
Qwen3-4B-Instruct 2026.02		15.8
Phi-4 2026.02		12.3
Glm-4-9B-Chat 2026.02		7.6
Ministral-3-14B-Instruct 2026.02		6
Phi-4-reasoning 2026.02		5.2
Llama-3.1-8B-Instruct 2026.02		3.2
Qwen3-30B-A3B-Thinking 2026.02		2
Glm-4-32B-0414 2026.02		1.2
Qwen3-30B-A3B-Instruct 2026.02		1
gpt-oss-120b 2026.02		1
Llama-3.3-70B-Instruct 2026.02		0
DeepSeek-V3.2 2026.02		0
Gemini 2.5 Flash 2026.02		0
DeepSeek-R1 2026.02		0
Gemini 2.5 Pro 2026.02		0