PROST
Models predict how objects move or change in everyday physical situations described in text. The benchmark tests reasoning about space and time.
- Made by
- Stéphane Aroca-Ouellette and colleagues
- Released
- June 2021
- Kind
- Commonsense
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- November 2019
- Scores refreshed
- November 20th, 2026
ALBERT V2 XL tops the leaderboard with 31.8% GPT-2 (1.5B) leads with 30.1%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-2 (1.5B), at 30.1%. This view shows only models we track, each at its best.
- 1 ALBERT V2 XL 31.8%
- 2 RoBERTa Large 31.3%
- 3 GPT-2 (1.5B) 30.1%
- 4 ALBERT V2 XXL 29.8%
- 5 ALBERT V2 Large 29.6%
- 6 RoBERTa Base 28.9%
- 7 GPT2 Medium 26.8%
- 8 ALBERT V2 Base 26.7%
- 9 BERT Large 26.7%
- 10 GPT2 Large 26.4%
- 11 GPT 26.1%
- 12 BERT Base 25.5%
- 13 GPT2 23.6%
Source: The PROST paper
- 1 GPT-2 (1.5B) 30.1%
Source: The PROST paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ALBERT V2 XL | 31.8% | Official leaderboard | ||
| 2 | RoBERTa Large | 31.3% | Official leaderboard | ||
| 3 | GPT-2 (1.5B) | 30.1% | Nov 2019 | Official leaderboard | |
| 4 | ALBERT V2 XXL | 29.8% | Official leaderboard | ||
| 5 | ALBERT V2 Large | 29.6% | Official leaderboard | ||
| 6 | RoBERTa Base | 28.9% | Official leaderboard | ||
| 7 | GPT2 Medium | 26.8% | Official leaderboard | ||
| 8 | ALBERT V2 Base | 26.7% | Official leaderboard | ||
| 9 | BERT Large | 26.7% | Official leaderboard | ||
| 10 | GPT2 Large | 26.4% | Official leaderboard | ||
| 11 | GPT | 26.1% | Official leaderboard | ||
| 12 | BERT Base | 25.5% | Official leaderboard | ||
| 13 | GPT2 | 23.6% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-2 (1.5B) | 30.1% | Nov 2019 | Official 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 PROST 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 years ago, in November 2019, for GPT-2 (1.5B). Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (13 entries).
- Pass Models scored 1 model we track, plus 12 other entries on its leaderboard.
- Warning Newest score The newest came 7 years ago, in November 2019, for GPT-2 (1.5B).
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 30.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 1 row for models we track and 12 other entries 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.