Benchmark Almanac

HEAD-QA v2

Llama 3.1-70B 83.2% leads since November 2025
Not in model cards

Models answer Spanish healthcare specialization exam questions across six disciplines. Version 2 adds languages, and the MedARC port runs the English configuration.

In March 2026, Llama 3.1 70B led the English zero-shot comparison at 83.15% accuracy. The table also includes Mixtral, Mistral, and Llama 3.1 8B.

Released
November 2025
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
Spanish, English
In and out
Text → Text
Interaction
Single turn
Run by
Anyone
Based on
HEAD-QA
Occupations
Healthcare practitioners and technical
Strongest model tested
Llama 3.1-70B #177 on the capability index
Last model added
July 2024
Scores refreshed
November 20th, 2026
4
Models scored in its paper

Llama 3.1-70B leads with 83.2% among models released by July 2024

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall accuracy, so this is the plain mean of its English and Spanish accuracies. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.

The newest model with a score here came out in July 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Llama 3.1-70B Zero-shot 83.2%
  2. 2 Mixtral 8x7B RAG 68.3%
  3. 3 Llama 3.1-8B Few-shot 66.5%
  4. 4 Mistral 7B v0.1 Few-shot 57.4%

Source: The HEAD-QA v2 paper

#ModelScoreSettingDateSource
1 Llama 3.1-70B 83.2% Zero-shot Jul 2024 Official leaderboard
2 Mixtral 8x7B 68.3% RAG Dec 2023 Official leaderboard
3 Llama 3.1-8B 66.5% Few-shot Jul 2024 Official leaderboard
4 Mistral 7B v0.1 57.4% Few-shot Sep 2023 Official leaderboard

Rankings by part

We read 2 parts from the benchmark’s paper: English and Spanish. Each ranks models on one part of the test. Llama 3.1-70B leads both. Arrows show how far a model moved from its overall rank among the models we track.

English

4 models we track have a score here.

  1. 1 Llama 3.1-70B 83.2%
  2. 2 Mixtral 8x7B 70.6%
  3. 3 Llama 3.1-8B 70.5%
  4. 4 Mistral 7B v0.1 60.6%

Scores at each effort level

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Llama 3.1-70B
Prob-based CoT
83.2%
Mixtral 8x7B
Prob-based CoT
68.3%
Llama 3.1-8B
Prob-based RAG Few-shot
66.5%
Mistral 7B v0.1
Prob-based CoT Zero-shot
57.4%

Source: The HEAD-QA v2 paper

ModelEffortHarnessScoreCost per taskOutput tokens
Llama 3.1-70B Zero-shot 83.2%
Llama 3.1-70B Few-shot 83.1%
Llama 3.1-70B RAG 82.5%
Llama 3.1-70B CoT 82.3%
Mixtral 8x7B RAG 68.3%
Mixtral 8x7B Few-shot 68.3%
Mixtral 8x7B Zero-shot 68.3%
Llama 3.1-8B Few-shot 66.5%
Llama 3.1-8B Zero-shot 66.2%
Mixtral 8x7B CoT 65.7%
Llama 3.1-8B CoT 65.1%
Llama 3.1-8B RAG 62.8%
Mistral 7B v0.1 Few-shot 57.4%
Mistral 7B v0.1 Zero-shot 56.2%
Mistral 7B v0.1 RAG 53.1%
Llama 3.1-70B Prob-based 52.8%
Mistral 7B v0.1 CoT 52.1%
Mixtral 8x7B Prob-based 50.4%
Mistral 7B v0.1 Prob-based 43.6%
Llama 3.1-8B Prob-based 41.5%

Number one over time

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

Meta
Benchmark paper Not tested since Nov 2025

Source: The HEAD-QA v2 paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3.1-70B Mixtral 8x7B Mistral 7B v0.1 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Llama 3.1-70B Mixtral 8x7B

Source: Official HEAD-QA 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 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in July 2024, for Llama 3.1-70B. 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 benchmark’s paper (4 entries).
  • Note Models scored Only 4 models we track.
  • Warning Newest score The newest came 2 years ago, in July 2024, for Llama 3.1-70B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3.1-70B (#177).
  • Pass Headroom The best is 83.2%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 20 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.

How we check