BIG-bench English Proverbs
Models read a short story and choose the English proverb that fits it. The 34 stories offer three to six choices each.
Google reports this task in its PaLM paper. Its later U-PaLM comparison reports 87.5 on the five-shot task.
- Made by
- Daniel Moseguí González
- Released
- January 2021
- Kind
- Reading comprehension
- 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
- December 2021
- Scores refreshed
- November 20th, 2026
PaLM 535b tops the leaderboard with 91.2% Gopher (280B) leads with 57.6%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 Gopher (280B), at 57.6%. This view shows only models we track, each at its best.
- 91.2 PaLM 535b
- 57.6
Gopher (280B)
- 50.0 PaLM 64b
- 47.1 BIG-G sparse 16m
- 44.1 BIG-G T=0 128b
- 44.1 BIG-G T=1 128b
- 44.1 GPT-3 200B
- 41.2 BIG-G sparse 8b
- 39.4 Gopher 7.1B
- 38.2 BIG-G sparse 1b
- 38.2 BIG-G sparse 244m
- 38.2 BIG-G sparse 422m
- 38.2 BIG-G T=0 16m
- 38.2 BIG-G T=0 1b
- 38.2 BIG-G T=0 422m
- 38.2 BIG-G T=1 16m
- 38.2 BIG-G T=1 1b
- 38.2 BIG-G T=1 422m
- 38.2 PaLM 8b
- 35.3 BIG-G sparse 4b
- 35.3 BIG-G T=0 27b
- 35.3 BIG-G T=0 2b
- 35.3 BIG-G T=0 4b
- 35.3 BIG-G T=1 27b
- 35.3 BIG-G T=1 2b
- 35.3 BIG-G T=1 4b
- 35.3 GPT-3 13B
- 35.3 GPT-3 Large
- 35.3 GPT-3 XL
- 35.3 GPT-3 Medium
- 33.3 Gopher 417M
- 33.3 Gopher 44M
- 32.4 BIG-G sparse 125m
- 32.4 BIG-G sparse 2b
- 32.4 BIG-G T=0 244m
- 32.4 BIG-G T=0 53m
- 32.4 BIG-G T=1 244m
- 32.4 BIG-G T=1 53m
- 32.4 GPT-3 6B
- 32.4 GPT-3 Small
- 29.4 BIG-G sparse 2m
- 29.4 BIG-G sparse 53m
- 29.4 BIG-G T=0 125m
- 29.4 BIG-G T=1 125m
- 29.4 GPT-3 3B
- 27.3 Gopher 117M
- 26.5 BIG-G T=0 2m
- 26.5 BIG-G T=1 2m
- 23.5 BIG-G T=0 8b
- 23.5 BIG-G T=1 8b
- 21.2 Gopher 1.4B
- 1 PaLM 535b 5-shot 91.2%
- 2
Gopher (280B) 5-shot 57.6%
- 3 PaLM 64b 1-shot 50%
- 4 BIG-G sparse 16m 1-shot, temperature 0 47.1%
- 5 BIG-G T=0 128b 1-shot, temperature 0 44.1%
- 6 BIG-G T=1 128b 1-shot, temperature 1 44.1%
- 7 GPT-3 200B 3-shot, temperature 0 44.1%
- 8 BIG-G sparse 8b 0-shot, temperature 0 41.2%
- 9 Gopher 7.1B 5-shot 39.4%
- 10 BIG-G sparse 1b 0-shot, temperature 0 38.2%
- 11 BIG-G sparse 244m 0-shot, temperature 0 38.2%
- 12 BIG-G sparse 422m 0-shot, temperature 0 38.2%
- 13 BIG-G T=0 16m 1-shot, temperature 0 38.2%
- 14 BIG-G T=0 1b 1-shot, temperature 0 38.2%
- 15 BIG-G T=0 422m 0-shot, temperature 0 38.2%
- 16 BIG-G T=1 16m 1-shot, temperature 1 38.2%
- 17 BIG-G T=1 1b 1-shot, temperature 1 38.2%
- 18 BIG-G T=1 422m 0-shot, temperature 1 38.2%
- 19 PaLM 8b 0-shot 38.2%
- 20 BIG-G sparse 4b 0-shot, temperature 0 35.3%
- 21 BIG-G T=0 27b 3-shot, temperature 0 35.3%
- 22 BIG-G T=0 2b 0-shot, temperature 0 35.3%
- 23 BIG-G T=0 4b 0-shot, temperature 0 35.3%
- 24 BIG-G T=1 27b 3-shot, temperature 1 35.3%
- 25 BIG-G T=1 2b 0-shot, temperature 1 35.3%
- 26 BIG-G T=1 4b 0-shot, temperature 1 35.3%
- 27 GPT-3 13B 0-shot, temperature 0 35.3%
- 28 GPT-3 Large 2-shot, temperature 0 35.3%
- 29 GPT-3 XL 0-shot, temperature 0 35.3%
- 30 GPT-3 Medium 2-shot, temperature 0 35.3%
- 31 Gopher 417M 5-shot 33.3%
- 32 Gopher 44M 5-shot 33.3%
- 33 BIG-G sparse 125m 2-shot, temperature 0 32.4%
- 34 BIG-G sparse 2b 0-shot, temperature 0 32.4%
- 35 BIG-G T=0 244m 0-shot, temperature 0 32.4%
- 36 BIG-G T=0 53m 0-shot, temperature 0 32.4%
- 37 BIG-G T=1 244m 0-shot, temperature 1 32.4%
- 38 BIG-G T=1 53m 0-shot, temperature 1 32.4%
- 39 GPT-3 6B 0-shot, temperature 0 32.4%
- 40 GPT-3 Small 1-shot, temperature 0 32.4%
- 41 BIG-G sparse 2m 1-shot, temperature 0 29.4%
- 42 BIG-G sparse 53m 1-shot, temperature 0 29.4%
- 43 BIG-G T=0 125m 0-shot, temperature 0 29.4%
- 44 BIG-G T=1 125m 0-shot, temperature 1 29.4%
- 45 GPT-3 3B 0-shot, temperature 0 29.4%
- 46 Gopher 117M 5-shot 27.3%
- 47 BIG-G T=0 2m 0-shot, temperature 0 26.5%
- 48 BIG-G T=1 2m 0-shot, temperature 1 26.5%
- 49 BIG-G T=0 8b 0-shot, temperature 0 23.5%
- 50 BIG-G T=1 8b 0-shot, temperature 1 23.5%
- 51 Gopher 1.4B 5-shot 21.2%
Source: Official BIG-bench English Proverbs leaderboard
- 1
Gopher (280B) 5-shot 57.6%
- 2 GPT-3 Medium 2-shot, temperature 0 35.3%
Source: Official BIG-bench English Proverbs leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | PaLM 535b 535B | 91.2% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 2 | | 57.6% | 5-shot | Dec 2021 | raw.githubusercontent.com | Official leaderboard |
| 3 | PaLM 64b 62.5B | 50% | 1-shot | raw.githubusercontent.com | Official leaderboard | |
| 4 | BIG-G sparse 16m 0.2B | 47.1% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 5 | BIG-G T=0 128b 137.7B | 44.1% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 6 | BIG-G T=1 128b 137.7B | 44.1% | 1-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 7 | GPT-3 200B 200B | 44.1% | 3-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 8 | BIG-G sparse 8b 60.3B | 41.2% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 9 | Gopher 7.1B 7.2B | 39.4% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 10 | BIG-G sparse 1b 7.6B | 38.2% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 11 | BIG-G sparse 244m 2.8B | 38.2% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 12 | BIG-G sparse 422m 4.1B | 38.2% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 13 | BIG-G T=0 16m 0B | 38.2% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 14 | BIG-G T=0 1b 1.1B | 38.2% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 15 | BIG-G T=0 422m 0.5B | 38.2% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 16 | BIG-G T=1 16m 0B | 38.2% | 1-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 17 | BIG-G T=1 1b 1.1B | 38.2% | 1-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 18 | BIG-G T=1 422m 0.5B | 38.2% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 19 | PaLM 8b 8.6B | 38.2% | 0-shot | raw.githubusercontent.com | Official leaderboard | |
| 20 | BIG-G sparse 4b 25.5B | 35.3% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 21 | BIG-G T=0 27b 29.2B | 35.3% | 3-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 22 | BIG-G T=0 2b 2.2B | 35.3% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 23 | BIG-G T=0 4b 3.7B | 35.3% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 24 | BIG-G T=1 27b 29.2B | 35.3% | 3-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 25 | BIG-G T=1 2b 2.2B | 35.3% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 26 | BIG-G T=1 4b 3.7B | 35.3% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 27 | GPT-3 13B 13B | 35.3% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 28 | GPT-3 Large 0.8B | 35.3% | 2-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 29 | GPT-3 XL 1.3B | 35.3% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 30 | GPT-3 Medium | 35.3% | 2-shot, temperature 0 | Jun 2020 | raw.githubusercontent.com | Official leaderboard |
| 31 | Gopher 417M 0.5B | 33.3% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 32 | Gopher 44M 0.1B | 33.3% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 33 | BIG-G sparse 125m 1.8B | 32.4% | 2-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 34 | BIG-G sparse 2b 17.3B | 32.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 35 | BIG-G T=0 244m 0.3B | 32.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 36 | BIG-G T=0 53m 0.1B | 32.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 37 | BIG-G T=1 244m 0.3B | 32.4% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 38 | BIG-G T=1 53m 0.1B | 32.4% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 39 | GPT-3 6B 6B | 32.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 40 | GPT-3 Small 0.1B | 32.4% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 41 | BIG-G sparse 2m 0.1B | 29.4% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 42 | BIG-G sparse 53m 0.5B | 29.4% | 1-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 43 | BIG-G T=0 125m 0.2B | 29.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 44 | BIG-G T=1 125m 0.2B | 29.4% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 45 | GPT-3 3B 3B | 29.4% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 46 | Gopher 117M 0.1B | 27.3% | 5-shot | raw.githubusercontent.com | Official leaderboard | |
| 47 | BIG-G T=0 2m 0B | 26.5% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 48 | BIG-G T=1 2m 0B | 26.5% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 49 | BIG-G T=0 8b 8.7B | 23.5% | 0-shot, temperature 0 | raw.githubusercontent.com | Official leaderboard | |
| 50 | BIG-G T=1 8b 8.7B | 23.5% | 0-shot, temperature 1 | raw.githubusercontent.com | Official leaderboard | |
| 51 | Gopher 1.4B 1.5B | 21.2% | 5-shot | raw.githubusercontent.com | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 57.6% | 5-shot | Dec 2021 | raw.githubusercontent.com | Official leaderboard |
| 2 | GPT-3 Medium | 35.3% | 2-shot, temperature 0 | Jun 2020 | raw.githubusercontent.com | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official BIG-bench English Proverbs 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 BIG-bench English Proverbs 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 4 years ago, in December 2021, for Gopher (280B). 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 (51 entries).
- Pass Models scored 2 models we track, plus 49 other entries on its leaderboard.
- Warning Newest score The newest came 4 years ago, in December 2021, for Gopher (280B).
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 57.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 5 rows for models we track and 49 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.