PoETa v2
Models answer multiple-choice and open-ended questions in Portuguese. The hub port selects native Portuguese tasks covering inference, reading, exams, proverbs and toxicity.
On November 19, 2026, the repository listed GPT-4.1 first at 76.2, followed by GPT-4o at 75.2 and Sabia 3 at 72.2.
- Made by
- PoETa v2 team
- Released
- September 2025
- Kind
- Knowledge in many languages
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Portuguese
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- GPT-4.1 #138 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
GPT-4.1 leads with 76.2 among models released by April 2025 GPT-4.1 leads with 76.2 among models released by April 2025
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 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
- 76.2 GPT-4.1
- 75.2 GPT-4o
- 72.2 Sabia 3
- 71.0
Qwen2.5-14B
- 70.5
Qwen3-14B
- 64.7
Qwen3-8B
- 63.7
Qwen2.5-7B
- 63.5 Falcon 3 10B
- 59.2
Qwen3-4B
- 58.8
Qwen2-7B
- 58.5 Falcon 3 7B
- 53.5
Llama 3.1-8B
- 53.1
Qwen2.5-3B
- 45.1
Qwen3-1.7B
- 43.0
Qwen2.5-1.5B
- 41.5
Llama 2-13B
- 41.1 Qwen 1 7B
- 38.6 Falcon 3 3B
- 38.4
Qwen2-1.5B
- 34.8 Curio 7B
- 32.4 Sabia
- 29.5
Llama 2-7B
- 19.9 Llama 1 7B
- 19.0 Qwen 1 1.8B
- 18.6 Falcon 3 1B
- 14.7 Curio 1.1B
- 10.2 Tinyllama 1T
- 1 GPT-4.1 76.2
- 2 GPT-4o Mar 2025 75.2
- 3 Sabia 3 72.2
- 4
Qwen2.5-14B 71.0
- 5
Qwen3-14B 70.5
- 6
Qwen3-8B 64.7
- 7
Qwen2.5-7B 63.7
- 8 Falcon 3 10B 63.5
- 9
Qwen3-4B 59.2
- 10
Qwen2-7B 58.8
- 11 Falcon 3 7B 58.5
- 12
Llama 3.1-8B 53.5
- 13
Qwen2.5-3B 53.1
- 14
Qwen3-1.7B 45.1
- 15
Qwen2.5-1.5B 43.0
- 16
Llama 2-13B 41.5
- 17 Qwen 1 7B 41.1
- 18 Falcon 3 3B 38.6
- 19
Qwen2-1.5B 38.4
- 20 Curio 7B 34.8
- 21 Sabia 32.4
- 22
Llama 2-7B 29.5
- 23 Llama 1 7B 19.9
- 24 Qwen 1 1.8B 19.0
- 25 Falcon 3 1B 18.6
- 26 Curio 1.1B 14.7
- 27 Tinyllama 1T 10.2
Source: Official PoETa v2 leaderboard
- 1 GPT-4.1 76.2
- 2 GPT-4o Mar 2025 75.2
- 3
Qwen2.5-14B 71.0
- 4
Qwen3-14B 70.5
- 5
Qwen3-8B 64.7
- 6
Qwen2.5-7B 63.7
- 7
Qwen3-4B 59.2
- 8
Qwen2-7B 58.8
- 9
Llama 3.1-8B 53.5
- 10
Qwen2.5-3B 53.1
- 11
Qwen3-1.7B 45.1
- 12
Qwen2.5-1.5B 43.0
- 13
Llama 2-13B 41.5
- 14
Qwen2-1.5B 38.4
- 15
Llama 2-7B 29.5
Source: Official PoETa v2 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4.1 | 76.2 | Apr 2025 | Official leaderboard | |
| 2 | GPT-4o Mar 2025 | 75.2 | Mar 2025 | Official leaderboard | |
| 3 | Sabia 3 | 72.2 | Official leaderboard | ||
| 4 | | 71.0 | Sep 2024 | Official leaderboard | |
| 5 | | 70.5 | Apr 2025 | Official leaderboard | |
| 6 | | 64.7 | Apr 2025 | Official leaderboard | |
| 7 | | 63.7 | Sep 2024 | Official leaderboard | |
| 8 | Falcon 3 10B 10B | 63.5 | Official leaderboard | ||
| 9 | | 59.2 | Apr 2025 | Official leaderboard | |
| 10 | | 58.8 | Jun 2024 | Official leaderboard | |
| 11 | Falcon 3 7B 7B | 58.5 | Official leaderboard | ||
| 12 | | 53.5 | Jul 2024 | Official leaderboard | |
| 13 | | 53.1 | Sep 2024 | Official leaderboard | |
| 14 | | 45.1 | Apr 2025 | Official leaderboard | |
| 15 | | 43.0 | Sep 2024 | Official leaderboard | |
| 16 | | 41.5 | Jul 2023 | Official leaderboard | |
| 17 | Qwen 1 7B 7B | 41.1 | Official leaderboard | ||
| 18 | Falcon 3 3B 3B | 38.6 | Official leaderboard | ||
| 19 | | 38.4 | Jun 2024 | Official leaderboard | |
| 20 | Curio 7B 7B | 34.8 | Official leaderboard | ||
| 21 | Sabia 7B | 32.4 | Official leaderboard | ||
| 22 | | 29.5 | Jul 2023 | Official leaderboard | |
| 23 | Llama 1 7B 7B | 19.9 | Official leaderboard | ||
| 24 | Qwen 1 1.8B 1.8B | 19.0 | Official leaderboard | ||
| 25 | Falcon 3 1B 1B | 18.6 | Official leaderboard | ||
| 26 | Curio 1.1B 1.1B | 14.7 | Official leaderboard | ||
| 27 | Tinyllama 1T 1.1B | 10.2 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4.1 | 76.2 | Apr 2025 | Official leaderboard | |
| 2 | GPT-4o Mar 2025 | 75.2 | Mar 2025 | Official leaderboard | |
| 3 | | 71.0 | Sep 2024 | Official leaderboard | |
| 4 | | 70.5 | Apr 2025 | Official leaderboard | |
| 5 | | 64.7 | Apr 2025 | Official leaderboard | |
| 6 | | 63.7 | Sep 2024 | Official leaderboard | |
| 7 | | 59.2 | Apr 2025 | Official leaderboard | |
| 8 | | 58.8 | Jun 2024 | Official leaderboard | |
| 9 | | 53.5 | Jul 2024 | Official leaderboard | |
| 10 | | 53.1 | Sep 2024 | Official leaderboard | |
| 11 | | 45.1 | Apr 2025 | Official leaderboard | |
| 12 | | 43.0 | Sep 2024 | Official leaderboard | |
| 13 | | 41.5 | Jul 2023 | Official leaderboard | |
| 14 | | 38.4 | Jun 2024 | Official leaderboard | |
| 15 | | 29.5 | Jul 2023 | 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 PoETa v2 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 PoETa v2 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for Qwen3-1.7B. 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 (27 entries).
- Pass Models scored 15 models we track, plus 12 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-1.7B.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4.1 (#138).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 15 rows 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.