List your company

Visual Planning on FrozenLake (Levels 3-8)

100Success Rate (Level 3)Gemini-3-Flash
9.5233.0156.579.99Jun 4, 2026

Evaluation results

MethodLinks
Gemini-3-FlashInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.061001009996849796
Gemini-2.5-ProInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0699978146444869.2
Qwen3-VL-32B-ThinkingInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0698795935282153.3
Kimi-K2.5Input Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0693777554485166.3
GPT-5Input Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0692655330383251.7
Gemini-2.5-FlashInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0692917458373364.2
Symbolic-Input Qwen3-VL-8BInput Modality=Symbolic, Reason=Oracle Upper Bound2026.0682726539434657.8
Symbolic-Input Qwen3-VL-4BInput Modality=Symbolic, Reason=Oracle Upper Bound2026.0679625140282647.7
MGSD-8BInput Modality=Visual, Task-specific training status=MGSD Trained2026.0678615839354051.8
Qwen3-VL-235B-A22B-InstructInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0677564420201839.2
MGSD-4BInput Modality=Visual, Task-specific training status=MGSD Trained2026.0676566027272445
GPT-4oInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0661382815121327.8
Claude-4.5-HaikuInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.064941291710625.3
Qwen3-VL-8B-InstructInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0642302718161324.3
Qwen3-VL-4B-InstructInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0633291953515.7
InternVL3-8BInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.06301814107914.7
Qwen2.5-VL-7B-InstructInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0618181187611.3
Qwen2.5-VL-3B-InstructInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.06148117448
LLaVA-OneVision-7BInput Modality=Visual, Prompting Strategy=Prompt-only, Task-specific training status=None2026.0613843315.3