Benchmark Almanac

HealthQA-BR

GPT-4.1 86.6% leads since June 2025
Not in model cards

Models answer Portuguese multiple-choice questions about clinical care and public health in Brazil’s Unified Health System.

Released
June 2025
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Portuguese
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Occupations
Community and social service, Healthcare practitioners and technical
Strongest model tested
GPT-4.1 #138 on the capability index
Last model added
April 2025
Scores refreshed
November 20th, 2026
21
Entries on its own leaderboard, 14 models we track

GPT-4.1 leads with 86.6% among models released by April 2025 GPT-4.1 leads with 86.6% 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:

  1. 1 GPT-4.1 86.6%
  2. 2 DeepSeek R1 (snapshot unspecified) 85.3%
  3. 3 GPT 4o (snapshot unspecified) 84.9%
  4. 4 Gemini 2.0 Flash Feb 2025 82.3%
  5. 5 GPT-4.1 mini 81.5%
  6. 6 Llama 4 Maverick 80.4%
  7. 7 Gemini 2.0 Flash-Lite 77.7%
  8. 8 Llama 3.3 70B 75.1%
  9. 9 Llama 4 Scout 74.1%
  10. 10 Gemma 3 27B 72.3%
  11. 11 GPT 4o Mini (snapshot unspecified) 71.8%
  12. 12 GPT-4.1 nano 69%
  13. 13 Gemma 3 12B 65.5%
  14. 14 EXAONE-3.5-32B-Instruct 53.1%
  15. 15 Gemma 3 4B 46.1%
  16. 16 ChatBode 7b 43.1%
  17. 17 Doutor Bode 7b 360k 42.1%
  18. 18 Doutor Bode 7b 240k 42%
  19. 19 InternLM2 Chat 7b 38.7%
  20. 20 Llama 3.1-8B 35.4%
  21. 21 Gemma 3 1B 28.4%

Source: Official HealthQA-BR leaderboard

#EntryScoreSettingDateSource
1 GPT-4.1 86.6% Apr 2025 Official leaderboard
2 DeepSeek R1 (snapshot unspecified) 85.3% Official leaderboard
3 GPT 4o (snapshot unspecified) 84.9% Official leaderboard
4 Gemini 2.0 Flash Feb 2025 82.3% Feb 2025 Official leaderboard
5 GPT-4.1 mini 81.5% Apr 2025 Official leaderboard
6 Llama 4 Maverick 80.4% Apr 2025 Official leaderboard
7 Gemini 2.0 Flash-Lite 77.7% Feb 2025 Official leaderboard
8 Llama 3.3 70B 75.1% Dec 2024 Official leaderboard
9 Llama 4 Scout 74.1% Apr 2025 Official leaderboard
10 Gemma 3 27B 72.3% Mar 2025 Official leaderboard
11 GPT 4o Mini (snapshot unspecified) 71.8% Official leaderboard
12 GPT-4.1 nano 69% Apr 2025 Official leaderboard
13 Gemma 3 12B 65.5% Mar 2025 Official leaderboard
14 EXAONE-3.5-32B-Instruct 53.1% Dec 2024 Official leaderboard
15 Gemma 3 4B 46.1% Mar 2025 Official leaderboard
16 ChatBode 7b 43.1% Official leaderboard
17 Doutor Bode 7b 360k 42.1% Official leaderboard
18 Doutor Bode 7b 240k 42% Official leaderboard
19 InternLM2 Chat 7b 38.7% Official leaderboard
20 Llama 3.1-8B 35.4% Jul 2024 Official leaderboard
21 Gemma 3 1B 28.4% Mar 2025 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4.1 86.6% Apr 2025 Official leaderboard
2 Gemini 2.0 Flash Feb 2025 82.3% Feb 2025 Official leaderboard
3 GPT-4.1 mini 81.5% Apr 2025 Official leaderboard
4 Llama 4 Maverick 80.4% Apr 2025 Official leaderboard
5 Gemini 2.0 Flash-Lite 77.7% Feb 2025 Official leaderboard
6 Llama 3.3 70B 75.1% Dec 2024 Official leaderboard
7 Llama 4 Scout 74.1% Apr 2025 Official leaderboard
8 Gemma 3 27B 72.3% Mar 2025 Official leaderboard
9 GPT-4.1 nano 69% Apr 2025 Official leaderboard
10 Gemma 3 12B 65.5% Mar 2025 Official leaderboard
11 EXAONE-3.5-32B-Instruct 53.1% Dec 2024 Official leaderboard
12 Gemma 3 4B 46.1% Mar 2025 Official leaderboard
13 Llama 3.1-8B 35.4% Jul 2024 Official leaderboard
14 Gemma 3 1B 28.4% Mar 2025 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Revalida, Enare Residência Médica and Enare Multiprofissional. Each ranks models on one part of the test. GPT-4.1 leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.

Revalida

14 models we track have a score here.

  1. 1 GPT-4.1 87.7%
  2. 2 GPT-4.1 mini ↑1 82.5%
  3. 3 Gemini 2.0 Flash Feb 2025 ↓1 82%
  4. 4 Llama 4 Maverick 80.6%
  5. 5 Gemini 2.0 Flash-Lite 77.5%
  6. 6 Llama 3.3 70B 75.7%
  7. 7 Gemma 3 27B ↑1 73.5%
  8. 8 Llama 4 Scout ↓1 71.5%
  9. 9 GPT-4.1 nano 67.9%
  10. 10 Gemma 3 12B 66.3%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Own leaderboard Passed 85% in Jun 2025, by GPT-4.1
GPT-4.1 86.6%

Source: Official HealthQA-BR leaderboard

GPT-4.1 on the official leaderboard passed 85% in April 2025

Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-4.1 Gemini 2.0 Flash Llama 3.3 70B EXAONE-3.5-32B-Instruct Llama 3.1-8B 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) GPT-4.1 Llama 3.3 70B

Source: Official HealthQA-BR 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 Law, finance and medicine

All 637 in Law, finance and medicine
  • MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy. Qwen 3.8 Max 80.4%
  • HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
  • HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
  • FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy. Ling-3.1-flash 81.7%
  • KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
  • Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (21 entries).
  • Pass Models scored 14 models we track, plus 7 other entries on its leaderboard.
  • Note Newest score The newest came 19 months ago, in April 2025, for GPT-4.1. That’s expected for a saturated test.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-4.1 (#138).
  • Note Headroom Saturated. The best is 86.6%, past 85% since April 2025.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 14 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.

How we check