Robo Use

Runs

Each run is a batch of trials of one model on one dataset.

GR00T N1.7-LIBERO · VLAarise-initiative/robosuite zero-shot probeSep 30, 202640%
pi0.5-LIBERO · VLAarise-initiative/robosuite zero-shot probeSep 30, 2026425%
GR00T N1.7-LIBERO · VLAfarama-foundation/metaworld zero-shot probeSep 30, 202630%
pi0.5-LIBERO · VLAfarama-foundation/metaworld zero-shot probeSep 30, 202630%
EVO1-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 202640100%
GR00T N1.7-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 20264095%
pi0-FAST-LIBERO (LeRobot) · VLAlifelong-robot-learning/liberoSep 30, 20263982%
pi0-LIBERO (LeRobot) · VLAlifelong-robot-learning/liberoSep 30, 20264075%
pi0-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 20264090%
pi0.5-LIBERO (LeRobot) · VLAlifelong-robot-learning/liberoSep 30, 20264092%
pi0.5-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 20264095%
SmolVLA-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 20264065%
VLA-JEPA-LIBERO · VLAlifelong-robot-learning/liberoSep 30, 20264095%
GR00T N1.7-LIBERO · VLAlifelong-robot-learning/libero-90 zero-shot probeSep 30, 202650%
pi0.5-LIBERO · VLAlifelong-robot-learning/libero-90 zero-shot probeSep 30, 202650%
Kimi K3 · mini-swe-agentbrave-eai/dexjocoSep 29, 2026140%
Kimi K3 · mini-swe-agentrobocasa/robocasaSep 29, 2026783%
Kimi K3 · Claude Codearise-initiative/robosuiteSep 28, 20262190%
Kimi K3 · mini-swe-agentarise-initiative/robosuiteSep 28, 20262193%
Kimi K3 · Claude Codebenchflow/robouse-droneSep 28, 20261070%
Kimi K3 · mini-swe-agentbenchflow/robouse-droneSep 28, 20261070%
Kimi K3 · Claude Codebenchflow/robouse-harmSep 28, 20268090%
Kimi K3 · mini-swe-agentbenchflow/robouse-harmSep 28, 20268085%
Kimi K3 · Claude Codebenchflow/robouse-menagerieSep 28, 20261573%
Kimi K3 · mini-swe-agentbenchflow/robouse-menagerieSep 28, 20261580%
Kimi K3 · Claude Codebenchflow/robouse-tabletopSep 28, 202611975%
Kimi K3 · mini-swe-agentbenchflow/robouse-tabletopSep 28, 202611965%
Kimi K3 · Claude Codebrave-eai/dexjocoSep 28, 2026140%
Kimi K3 · Claude Codefarama-foundation/gymnasium-roboticsSep 28, 20261275%
Kimi K3 · mini-swe-agentfarama-foundation/gymnasium-roboticsSep 28, 20261292%
Kimi K3 · Claude Codefarama-foundation/metaworldSep 28, 20265082%
Kimi K3 · mini-swe-agentfarama-foundation/metaworldSep 28, 20265080%
Kimi K3 · Claude Codelifelong-robot-learning/liberoSep 28, 20262060%
Kimi K3 · mini-swe-agentlifelong-robot-learning/liberoSep 28, 20262060%
Kimi K3 · Claude Coderobocasa/robocasaSep 28, 20267100%
GLM-5.3 · Claude Codearise-initiative/robosuiteSep 27, 20262185%
GLM-5.3 · Codexarise-initiative/robosuiteSep 27, 20262160%
GLM-5.3 · mini-swe-agentarise-initiative/robosuiteSep 27, 20262170%
GPT-6 Astra · Codexarise-initiative/robosuiteSep 27, 20262195%
GLM-5.3 · Claude Codebenchflow/robouse-droneSep 27, 20261080%
GLM-5.3 · Codexbenchflow/robouse-droneSep 27, 20261050%
GLM-5.3 · mini-swe-agentbenchflow/robouse-droneSep 27, 20261050%
GPT-6 Astra · Codexbenchflow/robouse-droneSep 27, 20261070%
GLM-5.3 · Claude Codebenchflow/robouse-harmSep 27, 20268088%
GLM-5.3 · Codexbenchflow/robouse-harmSep 27, 20268078%
GLM-5.3 · mini-swe-agentbenchflow/robouse-harmSep 27, 20268086%
GPT-6 Astra · Codexbenchflow/robouse-harmSep 27, 20268075%
GLM-5.3 · Claude Codebenchflow/robouse-menagerieSep 27, 20261567%
GLM-5.3 · Codexbenchflow/robouse-menagerieSep 27, 20261567%
GLM-5.3 · mini-swe-agentbenchflow/robouse-menagerieSep 27, 20261553%
GPT-6 Astra · Codexbenchflow/robouse-menagerieSep 27, 20261593%
GLM-5.3 · Claude Codebenchflow/robouse-tabletopSep 27, 202612844%
GLM-5.3 · Codexbenchflow/robouse-tabletopSep 27, 20264076%
GLM-5.3 · mini-swe-agentbenchflow/robouse-tabletopSep 27, 202611963%
GPT-6 Astra · Codexbenchflow/robouse-tabletopSep 27, 202611990%
MolmoAct2-LIBERO · VLAbenchflow/robouse-tabletopSep 27, 202650%
GLM-5.3 · Claude Codebrave-eai/dexjocoSep 27, 2026140%
GLM-5.3 · Codexbrave-eai/dexjocoSep 27, 20261450%
GLM-5.3 · mini-swe-agentbrave-eai/dexjocoSep 27, 2026140%
GPT-6 Astra · Codexbrave-eai/dexjocoSep 27, 20261444%
GLM-5.3 · Claude Codefarama-foundation/gymnasium-roboticsSep 27, 202612100%
GLM-5.3 · Codexfarama-foundation/gymnasium-roboticsSep 27, 20261291%
GLM-5.3 · mini-swe-agentfarama-foundation/gymnasium-roboticsSep 27, 20261292%
GPT-6 Astra · Codexfarama-foundation/gymnasium-roboticsSep 27, 202612100%
Opus 5.5 · Claude Codefarama-foundation/gymnasium-roboticsSep 27, 202612100%
GLM-5.3 · Claude Codefarama-foundation/metaworldSep 27, 20265080%
GLM-5.3 · Codexfarama-foundation/metaworldSep 27, 20265084%
GLM-5.3 · mini-swe-agentfarama-foundation/metaworldSep 27, 20265082%
GPT-6 Astra · Codexfarama-foundation/metaworldSep 27, 20265094%
MolmoAct2-LIBERO · VLAfarama-foundation/metaworldSep 27, 202650%
Opus 5.5 · Claude Codefarama-foundation/metaworldSep 27, 20265096%
GLM-5.3 · Claude Codelifelong-robot-learning/liberoSep 27, 20262063%
GLM-5.3 · Codexlifelong-robot-learning/liberoSep 27, 20262032%
GLM-5.3 · mini-swe-agentlifelong-robot-learning/liberoSep 27, 20262050%
GPT-6 Astra · Codexlifelong-robot-learning/liberoSep 27, 20262275%
MolmoAct2-LIBERO · VLAlifelong-robot-learning/liberoSep 27, 202620100%
Opus 5.5 · Claude Codelifelong-robot-learning/liberoSep 27, 20264·
GLM-5.3 · Claude Coderobocasa/robocasaSep 27, 2026783%
GLM-5.3 · Codexrobocasa/robocasaSep 27, 2026767%
GLM-5.3 · mini-swe-agentrobocasa/robocasaSep 27, 20267100%
GPT-6 Astra · Codexrobocasa/robocasaSep 27, 20267100%
GLM-5.3 · Claude Codestanfordvl/behavior-1kSep 27, 20265100%
GLM-5.3 · Codexstanfordvl/behavior-1kSep 27, 20265100%
GLM-5.3 · mini-swe-agentstanfordvl/behavior-1kSep 27, 20265100%