List your company

Embodied Task Planning on Robotouille Synchronous

97Pass@1 AccuracyGiG+Exp
-1.823.8549.575.15Jan 29, 2026

Evaluation results

MethodLinks
GiG+ExpLLM Backbone=Qwen3-235B-A22B-Instruct-2507-FP82026.0197
GiGLLM Backbone=Qwen3-235B-A22B-Instruct-2507-FP82026.0193
GiGLLM Backbone=Gemini-2.5-Flash2026.0192
ReActLLM Backbone=Gemini-2.5-Flash2026.0192
GiGLLM Backbone=DeepSeek-R1-FP42026.0191
GiG+ExpLLM Backbone=Gemini-2.5-Flash2026.0190
ReCAPLLM Backbone=Gemini-2.5-Flash2026.0189
GiG+ExpLLM Backbone=DeepSeek-R1-FP42026.0188
ReActLLM Backbone=Qwen3-235B-A22B-Instruct-2507-FP82026.0174
ReCAPLLM Backbone=DeepSeek-R1-FP42026.0172
ReCAPLLM Backbone=Qwen3-235B-A22B-Instruct-2507-FP82026.0171
ReActLLM Backbone=DeepSeek-R1-FP42026.0153
CoTLLM Backbone=Gemini-2.5-Flash2026.0134
CoTLLM Backbone=Qwen3-235B-A22B-Instruct-2507-FP82026.017
CoTLLM Backbone=DeepSeek-R1-FP42026.012