NaijaProverb-Bench
Models select the intended meaning of Nigerian proverbs from four choices. One track adds the original Igbo or Hausa wording when available.
The makers report a leaderboard for 18 models on both tracks. Nine of the 164 bilingual items use English alone.
- Made by
- Jane Odum and Ayodele Dada
- Released
- April 2026
- Kind
- Reasoning in many languages
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Gemini 3.1 Pro #40 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.1 Pro leads with 47.3% among models released by April 2026 Gemini 3.1 Pro leads with 47.3% among models released by April 2026
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. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, 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
- 47.3
Gemini 3.1 Pro
- 42.1
Gemini 3 Flash
- 41.5 GLM-5
- 41.5
Gemma 4 31B IT
- 40.9 Claude Sonnet 4.6
- 38.1 Claude Haiku 4.5
- 36.9 Claude Sonnet 4.5
- 36.9
Gemma 4 26B A4B
- 36.6
Gemini 2.5 Flash
- 35.1
Gemma 3 27B
- 34.1
DeepSeek-V3.1
- 32.9
DeepSeek-V3.2
- 29.0 GPT-5.4 Mini
- 28.4
Gemma 3 12B
- 28.4 Qwen 3 Next 80B Instruct
- 25.6 gpt-oss-20b
- 21.9
Gemma 3 4B
- 20.4 GPT-5.4 Nano
- 16.2
Gemma 3 1B
- 1
Gemini 3.1 Pro 47.3%
- 2
Gemini 3 Flash 42.1%
- 3 GLM-5 41.5%
- 4
Gemma 4 31B IT 41.5%
- 5 Claude Sonnet 4.6 40.9%
- 6 Claude Haiku 4.5 38.1%
- 7 Claude Sonnet 4.5 36.9%
- 8
Gemma 4 26B A4B 36.9%
- 9
Gemini 2.5 Flash Sep 2025 36.6%
- 10
Gemma 3 27B 35.1%
- 11
DeepSeek-V3.1 34.1%
- 12
DeepSeek-V3.2 32.9%
- 13 GPT-5.4 Mini 29%
- 14
Gemma 3 12B 28.4%
- 15 Qwen 3 Next 80B Instruct 28.4%
- 16 gpt-oss-20b 25.6%
- 17
Gemma 3 4B 21.9%
- 18 GPT-5.4 Nano 20.4%
- 19
Gemma 3 1B 16.2%
Source: Official NaijaProverb-Bench leaderboard
- 47.3
Gemini 3.1 Pro
- 42.1
Gemini 3 Flash
- 41.5 GLM-5
- 41.5
Gemma 4 31B IT
- 40.9 Claude Sonnet 4.6
- 38.1 Claude Haiku 4.5
- 36.9 Claude Sonnet 4.5
- 36.9
Gemma 4 26B A4B
- 36.6
Gemini 2.5 Flash
- 35.1
Gemma 3 27B
- 34.1
DeepSeek-V3.1
- 32.9
DeepSeek-V3.2
- 29.0 GPT-5.4 Mini
- 28.4
Gemma 3 12B
- 25.6 gpt-oss-20b
- 21.9
Gemma 3 4B
- 20.4 GPT-5.4 Nano
- 16.2
Gemma 3 1B
- 1
Gemini 3.1 Pro 47.3%
- 2
Gemini 3 Flash 42.1%
- 3 GLM-5 41.5%
- 4
Gemma 4 31B IT 41.5%
- 5 Claude Sonnet 4.6 40.9%
- 6 Claude Haiku 4.5 38.1%
- 7 Claude Sonnet 4.5 36.9%
- 8
Gemma 4 26B A4B 36.9%
- 9
Gemini 2.5 Flash Sep 2025 36.6%
- 10
Gemma 3 27B 35.1%
- 11
DeepSeek-V3.1 34.1%
- 12
DeepSeek-V3.2 32.9%
- 13 GPT-5.4 Mini 29%
- 14
Gemma 3 12B 28.4%
- 15 gpt-oss-20b 25.6%
- 16
Gemma 3 4B 21.9%
- 17 GPT-5.4 Nano 20.4%
- 18
Gemma 3 1B 16.2%
Source: Official NaijaProverb-Bench leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 47.3% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 2 | | 42.1% | Dec 2025 | Apr 2026 | Official leaderboard | |
| 3 | GLM-5 | 41.5% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 4 | | 41.5% | Apr 2026 | Apr 2026 | Official leaderboard | |
| 5 | Claude Sonnet 4.6 | 40.9% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 6 | Claude Haiku 4.5 | 38.1% | Oct 2025 | Apr 2026 | Official leaderboard | |
| 7 | Claude Sonnet 4.5 | 36.9% | Sep 2025 | Apr 2026 | Official leaderboard | |
| 8 | | 36.9% | Apr 2026 | Apr 2026 | Official leaderboard | |
| 9 | | 36.6% | Sep 2025 | Apr 2026 | Official leaderboard | |
| 10 | | 35.1% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 11 | | 34.1% | Aug 2025 | Apr 2026 | Official leaderboard | |
| 12 | | 32.9% | Dec 2025 | Apr 2026 | Official leaderboard | |
| 13 | GPT-5.4 Mini | 29% | Mar 2026 | Apr 2026 | Official leaderboard | |
| 14 | | 28.4% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 15 | Qwen 3 Next 80B Instruct | 28.4% | Apr 2026 | Official leaderboard | ||
| 16 | gpt-oss-20b | 25.6% | Aug 2025 | Apr 2026 | Official leaderboard | |
| 17 | | 21.9% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 18 | GPT-5.4 Nano | 20.4% | Mar 2026 | Apr 2026 | Official leaderboard | |
| 19 | | 16.2% | Mar 2025 | Apr 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 47.3% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 2 | | 42.1% | Dec 2025 | Apr 2026 | Official leaderboard | |
| 3 | GLM-5 | 41.5% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 4 | | 41.5% | Apr 2026 | Apr 2026 | Official leaderboard | |
| 5 | Claude Sonnet 4.6 | 40.9% | Feb 2026 | Apr 2026 | Official leaderboard | |
| 6 | Claude Haiku 4.5 | 38.1% | Oct 2025 | Apr 2026 | Official leaderboard | |
| 7 | Claude Sonnet 4.5 | 36.9% | Sep 2025 | Apr 2026 | Official leaderboard | |
| 8 | | 36.9% | Apr 2026 | Apr 2026 | Official leaderboard | |
| 9 | | 36.6% | Sep 2025 | Apr 2026 | Official leaderboard | |
| 10 | | 35.1% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 11 | | 34.1% | Aug 2025 | Apr 2026 | Official leaderboard | |
| 12 | | 32.9% | Dec 2025 | Apr 2026 | Official leaderboard | |
| 13 | GPT-5.4 Mini | 29% | Mar 2026 | Apr 2026 | Official leaderboard | |
| 14 | | 28.4% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 15 | gpt-oss-20b | 25.6% | Aug 2025 | Apr 2026 | Official leaderboard | |
| 16 | | 21.9% | Mar 2025 | Apr 2026 | Official leaderboard | |
| 17 | GPT-5.4 Nano | 20.4% | Mar 2026 | Apr 2026 | Official leaderboard | |
| 18 | | 16.2% | Mar 2025 | Apr 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: naijaproverb_v3 and naijaproverb_bilingual. Each ranks models on one part of the test. Gemini 3.1 Pro leads both. Arrows show how far a model moved from its overall rank among the models we track.
naijaproverb_v3
18 models we track have a score here.
- 1
Gemini 3.1 Pro 49.4%
- 2
Gemini 3 Flash 47%
- 3 GLM-5 45.7%
- 4 Claude Sonnet 4.6 ↑1 45.7%
- 5 Claude Haiku 4.5 ↑1 42.1%
- 6
Gemma 4 31B IT ↓2 42.1%
- 7
Gemini 2.5 Flash Sep 2025 ↑2 39.6%
- 8
Gemma 4 26B A4B 39.6%
- 9
DeepSeek-V3.1 ↑2 38.4%
- 10 Claude Sonnet 4.5 ↓3 38.4%
naijaproverb_bilingual
18 models we track have a score here.
- 1
Gemini 3.1 Pro 45.1%
- 2
Gemma 4 31B IT ↑2 40.9%
- 3
Gemini 3 Flash ↓1 37.2%
- 4 GLM-5 ↓1 37.2%
- 5 Claude Sonnet 4.6 36%
- 6 Claude Sonnet 4.5 ↑1 35.4%
- 7
Gemma 3 27B ↑3 34.8%
- 8 Claude Haiku 4.5 ↓2 34.1%
- 9
Gemma 4 26B A4B ↓1 34.1%
- 10
Gemini 2.5 Flash Sep 2025 ↓1 33.5%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official NaijaProverb-Bench 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 NaijaProverb-Bench 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 Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Gemma 4 26B A4B. 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 (19 entries).
- Pass Models scored 18 models we track, plus 1 other entry on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Gemma 4 26B A4B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.1 Pro (#40).
- Pass Headroom The best is 47.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 18 rows for models we track and 1 other entry 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.