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

Planning research benchmarks – Page 3 · SOTA2 Research

Planning

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Planning OOD Trips Meetings Calendar

Qwen3-14B pass@1

38.7Trips Planned Count

15

Apr 23, 2026

Planning Benchmark Domains

105BW Score

15

Apr 3, 2026

Bench2Drive (test)

74.22Driving Score

15

Mar 20, 2026

0.22L2 Error

15

Feb 26, 2026

T-Eval official subset (test)

Qwen2.5-72B-Instruct

92.2Precision

14

Jul 7, 2026

nuPlan (test-random)

CorrectionPlanner

91.14Planner Score

14

Mar 18, 2026

nuPlan Hard (test)

CorrectionPlanner

77.29Planner Score

14

Mar 18, 2026

Bench2Drive open-loop

0.73Average L2 Error

14

Mar 19, 2026

Countdown (held-out)

87.96Pass@1

14

Mar 4, 2026

NuInteract (test)

82.64Accuracy

13

Feb 27, 2026

LLM-BabyBench Planning

89.33Accuracy

12

Jun 24, 2026

99.2NC

12

May 21, 2026

59.25Pass@1

12

Apr 14, 2026

Blocks (Blocksworld)

Stick-Breaking Transformer

100Accuracy

12

Mar 12, 2026

nuPlan interPlanLC

84.53CLS-R

12

Feb 26, 2026

46Validity Rate

12

Feb 26, 2026

63Validity Rate

12

Feb 26, 2026

57Validity Rate

12

Feb 26, 2026

89Validity Rate

12

Feb 26, 2026

nuScenes resume from stop

0.13L2 Error (1s)

12

Feb 26, 2026

nuScenes 3-point turn

0.28Trajectory L2 Error (1s)

12

Feb 26, 2026

Sokoban unseen problems

FD-LAMA-anytime

100Completion Rate

11

Jun 2, 2026

Labyrinth unseen problems

OCLGen (uniform)

100Completion Rate

11

Jun 2, 2026

Logistics unseen problems

OCLGen (uniform)

100Completion Rate

11

Jun 2, 2026

Blocksworld unseen problems

OCLGen (uniform)

100Completion Rate

11

Jun 2, 2026

Page 3 of 12

Popular datasets

nuScenes BlocksWorld TravelPlanner NAVSIM Sokoban

Follow for updates

Join SOTA2 Contact