BIG-bench Abstract Narrative Understanding
Models select the English proverb that best fits a short story. Three versions offer five, ten or 100 choices.
The BIG-bench task uses 100 proverbs from ePiC. ADAGE ranks eight models on the five-choice version with 1,000 stories.
- Released
- June 2021
- Kind
- Language reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- English
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
-
Qwen3-32B #135 on the capability index
- Last model added
- August 2025
- Scores refreshed
- November 20th, 2026
Qwen3-14B leads with 82.5% among models released by August 2025
Best score per model from ADAGE’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in August 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
Qwen3-14B Five choices 82.5%
- 2
Qwen3-32B Five choices 82%
- 3
Qwen3-8B Five choices 79.8%
- 4
Qwen3-4B Five choices 77.8%
- 5
Gemma 3 4B Five choices 62.4%
- 6
Qwen3-1.7B Five choices 57.4%
- 7
Gemma 3 1B Five choices 32%
- 8
Gemma 3 270M Five choices 18.4%
Source: ADAGE’s leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 82.5% | Five choices | Apr 2025 | Official leaderboard |
| 2 | | 82% | Five choices | Apr 2025 | Official leaderboard |
| 3 | | 79.8% | Five choices | Apr 2025 | Official leaderboard |
| 4 | | 77.8% | Five choices | Apr 2025 | Official leaderboard |
| 5 | | 62.4% | Five choices | Mar 2025 | Official leaderboard |
| 6 | | 57.4% | Five choices | Apr 2025 | Official leaderboard |
| 7 | | 32% | Five choices | Mar 2025 | Official leaderboard |
| 8 | | 18.4% | Five choices | Aug 2025 | Official leaderboard |
2 models have held number one on ADAGE’s leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: ADAGE’s leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: ADAGE’s 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 15 months ago, in August 2025, for Gemma 3 270M. 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 official leaderboard (8 entries).
- Pass Models scored 8 models we track.
- Warning Newest score The newest came 15 months ago, in August 2025, for Gemma 3 270M.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-32B (#135).
- Pass Headroom The best is 82.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on ADAGE: 8 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.