List your company
ResearchFormerly WizWand

Interactive Decision Making on Textcraft

99.6Success RateGPT-4o-1120
-2.496824.009150.51577.0209May 13, 2026May 16, 2026May 19, 2026May 23, 2026May 26, 2026May 29, 2026Jun 2, 2026
Updated 4mo ago

Evaluation results

MethodLinks
GPT-4o-1120Paradigm=MAP, Model Category=Non-reasoning Models2026.0599.6
Deepseek-V4-ProParadigm=MAP, Model Category=Reasoning Models2026.0599.5
Kimi-K2-ThinkingParadigm=MAP, Model Category=Reasoning Models2026.0599.2
Deepseek-V4-ProParadigm=CoMAP, Model Category=Reasoning Models2026.0599.2
Deepseek-V4-ProParadigm=ReAct, Model Category=Reasoning Models2026.0598.8
Kimi-K2-ThinkingParadigm=CoMAP, Model Category=Reasoning Models2026.0597.6
Kimi-K2-ThinkingParadigm=ReAct, Model Category=Reasoning Models2026.0596.8
GPT-4o-0806Paradigm=MAP, Model Category=Non-reasoning Models2026.0596.7
GPT-4o-1120Paradigm=CoMAP, Model Category=Non-reasoning Models2026.0596.7
Minimax-M2.7Paradigm=MAP, Model Category=Reasoning Models2026.0596.7
MAP-4BParadigm=MAP, Model Category=Fine-Tuning Models2026.0595.6
GPT-4o-1120Paradigm=ReAct, Model Category=Non-reasoning Models2026.0594.7
GPT-4o-0806Paradigm=CoMAP, Model Category=Non-reasoning Models2026.0592.5
Minimax-M2.7Paradigm=ReAct, Model Category=Reasoning Models2026.0592.3
MAP-4BParadigm=CoMAP, Model Category=Fine-Tuning Models2026.0592.3
Minimax-M2.7Paradigm=CoMAP, Model Category=Reasoning Models2026.0592.1
GPT-4o-0806Paradigm=ReAct, Model Category=Non-reasoning Models2026.0591.6
MAP-4BParadigm=ReAct, Model Category=Fine-Tuning Models2026.0591.2
Qwen3-32B-ThinkingParadigm=MAP, Model Category=Reasoning Models2026.0590.4
Qwen3-32B-ThinkingParadigm=CoMAP, Model Category=Reasoning Models2026.0587.7
Qwen3-8B-ThinkingParadigm=MAP, Model Category=Reasoning Models2026.0587.1
Qwen3-32B-ThinkingParadigm=ReAct, Model Category=Reasoning Models2026.0582.4
ACT-4BParadigm=MAP, Model Category=Fine-Tuning Models2026.0579.4
GPT-4o-miniParadigm=MAP, Model Category=Non-reasoning Models2026.0575.6
ACT-4BParadigm=CoMAP, Model Category=Fine-Tuning Models2026.0574.5
Qwen3-4B-InstructParadigm=MAP, Model Category=Non-reasoning Models2026.0571.9
ACT-4BParadigm=ReAct, Model Category=Fine-Tuning Models2026.0570.1
Doubao-Seed-2.0-ProParadigm=MAP, Model Category=Reasoning Models2026.0569.8
Qwen3-8B-ThinkingParadigm=CoMAP, Model Category=Reasoning Models2026.0567
Qwen3-30B-A3B-InstructParadigm=MAP, Model Category=Non-reasoning Models2026.0566.6
Qwen3-8B-ThinkingParadigm=ReAct, Model Category=Reasoning Models2026.0566.4
Doubao-Seed-2.0-ProParadigm=CoMAP, Model Category=Reasoning Models2026.0565.6
Doubao-Seed-2.0-ProParadigm=ReAct, Model Category=Reasoning Models2026.0563.1
Qwen3-4B-ThinkingParadigm=MAP, Model Category=Reasoning Models2026.0559.6
Qwen3-30B-A3B-InstructParadigm=CoMAP, Model Category=Non-reasoning Models2026.0558.6
Qwen3-30B-A3B-InstructParadigm=ReAct, Model Category=Non-reasoning Models2026.0556.8
GPT-4o-miniParadigm=CoMAP, Model Category=Non-reasoning Models2026.0554.2
GPT-4o-miniParadigm=ReAct, Model Category=Non-reasoning Models2026.0546.5
Multi2Base Model=Mistral 7B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.0644.5
Qwen3-4B-ThinkingParadigm=CoMAP, Model Category=Reasoning Models2026.0537.5
Qwen3-4B-InstructParadigm=CoMAP, Model Category=Non-reasoning Models2026.0537.1
Qwen3-4B-ThinkingParadigm=ReAct, Model Category=Reasoning Models2026.0535.6
Multi2Base Model=Llama-3.1 8B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.0635.6
Qwen3-4B-InstructParadigm=ReAct, Model Category=Non-reasoning Models2026.0531.8
ADaPTBase Model=Mistral 7B, Training Type=Prompt-based, Structure Type=Hierarchical2026.0630.2
Multi2Base Model=Qwen-2.5 3B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.0628.5
GliderBase Model=Mistral 7B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.0628.5
ReflexionBase Model=Mistral 7B, Training Type=Prompt-based, Structure Type=Single2026.0623.16
ReActBase Model=Mistral 7B, Training Type=Prompt-based, Structure Type=Single2026.0623
ADaPTBase Model=Qwen-2.5 3B, Training Type=Prompt-based, Structure Type=Hierarchical2026.0621
GliderBase Model=Qwen-2.5 3B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.0618.5
GRPOBase Model=Mistral 7B, Training Type=Fine-tuning-based, Structure Type=Single2026.0611
ReflexionBase Model=Llama-3.1 8B, Training Type=Prompt-based, Structure Type=Single2026.0611
GliderBase Model=Llama-3.1 8B, Training Type=Fine-tuning-based, Structure Type=Hierarchical2026.069.5
ReActBase Model=Llama-3.1 8B, Training Type=Prompt-based, Structure Type=Single2026.069
GRPOBase Model=Llama-3.1 8B, Training Type=Fine-tuning-based, Structure Type=Single2026.065.5
ADaPTBase Model=Llama-3.1 8B, Training Type=Prompt-based, Structure Type=Hierarchical2026.065
GRPOBase Model=Qwen-2.5 3B, Training Type=Fine-tuning-based, Structure Type=Single2026.063.5
ReActBase Model=Qwen-2.5 3B, Training Type=Prompt-based, Structure Type=Single2026.063
ReflexionBase Model=Qwen-2.5 3B, Training Type=Prompt-based, Structure Type=Single2026.061.43