Benchmark Almanac

SMM4H-HeaRD 2026 Multilingual Adverse Drug Event Detection

Bhramastra 0.67 tops its leaderboard
Not in model cards
Version 2026

Models flag personal reports of drug side effects in seven languages. The organizers withheld Farsi from training and added 15,184 Farsi posts at test time.

Bhramastra paired a multilingual detector with Gemini 2.5 Flash. Its system scored 0.6653 average F1 and 0.5863 on Farsi.

Released
November 2025
Kind
Medicine
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
Public, plus a private test set
Measures
Capability
Subject
Health sciences
Language
Many languages
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Run by
A host
12
Entries in its paper, 0 models we track

Bhramastra tops the leaderboard with 0.67

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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.

  1. 1 Bhramastra 0.67
  2. 2 DNT 0.66
  3. 3 MedMind AI 0.65
  4. 4 IITPatna_ADE 0.62
  5. 5 Limics 0.61
  6. 6 Vinland_Vector 0.61
  7. 7 Gladiators 0.60
  8. 8 Paradise 0.60
  9. 9 Cuet_Data_Wizards 0.58
  10. 10 blue 0.58
  11. 11 TIET 0.50
  12. 12 Creative Catalysts 0.39

Source: The SMM4H-HeaRD 2026 Multilingual Adverse Drug Event Detection paper

#EntryScoreSettingSubmitted byDateSource
1 Bhramastra 0.67 Bhramastra Official leaderboard
2 DNT 0.66 DNT Official leaderboard
3 MedMind AI 0.65 MedMind AI Official leaderboard
4 IITPatna_ADE 0.62 IITPatna_ADE Official leaderboard
5 Limics 0.61 Limics Official leaderboard
6 Vinland_Vector 0.61 Vinland_Vector Official leaderboard
7 Gladiators 0.60 Gladiators Official leaderboard
8 Paradise 0.60 Paradise Official leaderboard
9 Cuet_Data_Wizards 0.58 Cuet_Data_Wizards Official leaderboard
10 blue 0.58 blue Official leaderboard
11 TIET 0.50 TIET Official leaderboard
12 Creative Catalysts 0.39 Creative Catalysts Official 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.

Versions

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 Public tasks, plus a private test set.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 12 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on codabench.org: 12 entries at the last read, none a model we track.
  • 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