PlanBench
Models construct action sequences that reach a goal under stated planning rules. A planning validator checks whether each plan satisfies action preconditions and achieves the goal.
The static leaderboard separates ordinary and renamed Blocksworld tasks. PlanBench-XL in the almanac is an unrelated tool-use benchmark.
- Made by
- Arizona State University and Colorado State University
- Released
- June 2022
- Kind
- Abstract puzzles and logic
- Level
- School
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
DeepSeek-R1 #130 on the capability index
- Last model added
- January 2025
- Scores refreshed
- November 20th, 2026
In the authors’ words
Generating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has become a hot topic of research. Most claims about LLM planning capabilities are however based on common sense tasks-where it becomes hard to tell whether LLMs are planning or merely retrieving from their vast world knowledge. There is a strong need for systematic and extensible planning benchmarks with sufficient diversity to evaluate whether LLMs have innate planning capabilities. Motivated by this, we propose PlanBench, an extensible benchmark suite based on the kinds of domains used in the automated planning community, especially in the International Planning Competition, to test the capabilities of LLMs in planning or reasoning about actions and change. PlanBench provides sufficient diversity in both the task domains and the specific planning capabilities. Our studies also show that on many critical capabilities-including plan generation-LLM performance falls quite short, even with the SOTA models. PlanBench can thus function as a useful marker of progress of LLMs in planning and reasoning.
DeepSeek-R1 leads with 55.5% among models released by January 2025
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. The board reports no overall score, so the headline is the plain mean of its four domain success rates. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in January 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
DeepSeek-R1 Zero-shot 55.5%
- 2 o1-preview Zero-shot 52.9%
- 3 o1-mini Zero-shot 22.3%
Source: Official PlanBench leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 55.5% | Zero-shot | Jan 2025 | Official leaderboard |
| 2 | o1-preview | 52.9% | Zero-shot | Sep 2024 | Official leaderboard |
| 3 | o1-mini | 22.3% | Zero-shot | Sep 2024 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Blocksworld, Mystery Blocksworld and Randomized Mystery Blocksworld. DeepSeek-R1 leads 2 of them, and o1-preview leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Blocksworld
3 models we track have a score here.
- 1
DeepSeek-R1 99.1%
- 2 o1-preview 97.8%
- 3 o1-mini 56.6%
Mystery Blocksworld
3 models we track have a score here.
- 1 o1-preview ↑1 52.8%
- 2
DeepSeek-R1 ↓1 43.3%
- 3 o1-mini 19.1%
Randomized Mystery Blocksworld
3 models we track have a score here.
- 1 o1-preview ↑1 37.3%
- 2
DeepSeek-R1 ↓1 25.8%
- 3 o1-mini 3.50%
Blocksworld Hard
3 models we track have a score here.
- 1
DeepSeek-R1 53.6%
- 2 o1-preview 23.6%
- 3 o1-mini 10%
2 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PlanBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PlanBench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 22 months ago, in January 2025, for DeepSeek-R1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (3 entries).
- Note Models scored Only 3 models we track.
- Warning Newest score The newest came 22 months ago, in January 2025, for DeepSeek-R1.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-R1 (#130).
- Pass Headroom The best is 55.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 3 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.