List your company

Agent Behavior Adaptation on BlocksWorld (BW) (test)

51Loop RatioMistral-7B-Instruct
-2.0411.7325.539.27Feb 2, 2026

Evaluation results

MethodLinks
Mistral-7B-InstructModel Type=Non-thinking Model2026.0251
Qwen3-4B-ThinkingModel Type=Thinking Model2026.0228.5
Qwen3-4B-InstructModel Type=Non-thinking Model2026.0215.8
Phi-4Model Type=Non-thinking Model2026.0212.3
Glm-4-9B-ChatModel Type=Non-thinking Model2026.027.6
Ministral-3-14B-InstructModel Type=Non-thinking Model2026.026
Phi-4-reasoningModel Type=Thinking Model2026.025.2
Llama-3.1-8B-InstructModel Type=Non-thinking Model2026.023.2
Qwen3-30B-A3B-ThinkingModel Type=Thinking Model2026.022
Glm-4-32B-0414Model Type=Non-thinking Model2026.021.2
Qwen3-30B-A3B-InstructModel Type=Non-thinking Model2026.021
gpt-oss-120bModel Type=Thinking Model2026.021
Llama-3.3-70B-InstructModel Type=Non-thinking Model2026.020
DeepSeek-V3.2Model Type=Non-thinking Model2026.020
Gemini 2.5 FlashModel Type=Non-thinking Model2026.020
DeepSeek-R1Model Type=Thinking Model2026.020
Gemini 2.5 ProModel Type=Thinking Model2026.020