AmbiStory
Models rate how plausible a word meaning is in a short story. The shared task averages rank correlation and accuracy within the organizers’ tolerance.
The SemEval test contains 930 examples with human ratings. The organizers report 78 participants on the evaluation leaderboard. Teams ran Qwen3, GPT-5 and Gemini.
- Released
- July 2025
- Kind
- Reading comprehension
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts, Written by crowdworkers
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Llama 3.1-8B #203 on the capability index
- Last model added
- July 2024
- Scores refreshed
- November 20th, 2026
ChulaNLP + DeepSeek-V3.2-Exp tops the leaderboard with 0.77 Llama 3.1-8B leads with 0.56
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is Llama 3.1-8B, at 0.56. Agents built around a model, such as ChulaNLP + DeepSeek-V3.2-Exp, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
- 1 ChulaNLP + DeepSeek-V3.2-Exp 0.77
- 2 GPT-4o (snapshot unspecified) 0.76
- 3 DeBERTa-xLarge 0.74
- 4 DeBERTa-v3-large 0.73
- 5 DeBERTa-v3-base 0.65
- 6 nli-mpnet-base-v2 0.64
- 7 BERT-base 0.57
- 8
Llama 3.1-8B Organizer baseline 0.56
- 9 DistilBERT 0.36
Source: Official AmbiStory leaderboard
Source: Official AmbiStory leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | ChulaNLP + DeepSeek-V3.2-Exp | 0.77 | ChulaNLP | Sep 2025 | Official leaderboard | |
| 2 | GPT-4o (snapshot unspecified) | 0.76 | NCL-UoR | NCL-UoR | Official leaderboard | |
| 3 | DeBERTa-xLarge | 0.74 | ConText | ConText | Official leaderboard | |
| 4 | DeBERTa-v3-large | 0.73 | Guys_LLM | Guys_LLM | Official leaderboard | |
| 5 | DeBERTa-v3-base | 0.65 | Habib Disambiguators | Habib Disambiguators | Official leaderboard | |
| 6 | nli-mpnet-base-v2 | 0.64 | SemTechLab | SemTechLab | Official leaderboard | |
| 7 | BERT-base | 0.57 | blue | blue | Official leaderboard | |
| 8 | | 0.56 | Organizer baseline | Jul 2024 | Official leaderboard | |
| 9 | DistilBERT | 0.36 | Narrative Team | Narrative Team | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | | 0.56 | Organizer baseline | Jul 2024 | 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 AmbiStory 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in July 2024, for Llama 3.1-8B. 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 (9 entries).
- Pass Models scored 1 model we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in July 2024, for Llama 3.1-8B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3.1-8B (#203).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 7 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.