Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Task Planning research benchmarks – Page 3 · SOTA2 Research

Task Planning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Tower of Hanoi 1.0 (test)

4.29Avg Planning Time (s)

3

Feb 26, 2026

Rearrangement 1.0 (test)

15.74Average Planning Time Cost (s)

3

Feb 26, 2026

Stack 1.0 (test)

5.94Average Planning Time Cost (s)

3

Feb 26, 2026

Task Planning Evaluation Dataset sequential tasks GPT-4 annotated (test)

0.54Edit Distance

3

Feb 26, 2026

HuggingGPT Evaluation Dataset graph tasks GPT-4 annotated

50.48GPT-4 Score

3

Feb 26, 2026

HuggingGPT Human Evaluation Set 130 diverse requests (test)

0.912Passing Rate

3

Feb 26, 2026

HuggingGPT Task Planning (Single Task)

52.62Accuracy

3

Feb 26, 2026

SheetCopilot 10% subset 1.0

85Exec@1

3

Feb 26, 2026

Collaborative Path Planning Scene 5 (Ramp-mediated detour) 1.0 (test)

93.13PS

2

Mar 24, 2026

Collaborative Path Planning Scene 4 (Z-turn fire extinguisher localization) 1.0 (test)

97.06PS

2

Mar 24, 2026

Collaborative Path Planning Scene 3 (Bilateral-passable pillar) 1.0 (test)

97.13PS Score

2

Mar 24, 2026

Collaborative Path Planning Scene 2 (Unilateral-access narrow pillar) 1.0 (test)

99.23Planning Success (PS)

2

Mar 24, 2026

Collaborative Path Planning Scene 1 (L-turn sofa search) 1.0 (test)

82.19PS Score

2

Mar 24, 2026

Monoculture Environment Multiple Plant - Multiple Target

66.67Success Rate

2

Feb 26, 2026

Monoculture Environment Multiple Plant - Single Target

80Success Rate

2

Feb 26, 2026

Monoculture Environment Single Plant - Multiple Target

80Success Rate

2

Feb 26, 2026

Monoculture Environment Single Plant - Single Target

90Success Rate

2

Feb 26, 2026

Table rearrangement Office Scenario 1.0 (test)

191Time (s)

2

Feb 26, 2026

Chair rearrangement Office Scenario 1.0 (test)

154Time (s)

2

Feb 26, 2026

Bin rearrangement Office Scenario 1.0 (test)

224Time (s)

2

Feb 26, 2026

SheetCopilot 100% full 1.0

87.3Exec@1

2

Feb 26, 2026

Core Robotic Capabilities

—

—Primary metric

0

Jul 7, 2026

Embodied Task Planning (test)

—

—Primary metric

0

Feb 26, 2026

Page 3 of 3

Popular datasets

ProcTHOR Collaborative Path Planning Monoculture Environment TaskBench Shortsighted Monkey

Follow for updates

Join SOTA2 Contact