Benchmark Almanac

PharmaBench (micro1)

Kimi K3.1 Pro 27.5% leads since October 2026
Not in model cards

Agents write clinical trial documentation inside 8 synthetic drug programs, across 120 tasks written by biostatisticians, medical writers, safety physicians and regulatory staff.

Penalties subtract for content an expert would have to remove. Full marks were rare. Not the 2024 PharmaBench of ADMET data.

Made by
micro1
Released
October 2026
Kind
Medicine
Level
Expert
Scored
Graded by a model
Answers
Agent task
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last model added
November 2026
Scores refreshed
November 12th, 2026
13
Models scored on its own leaderboard

Kimi K3.1 Pro leads with 27.5%

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

13 models. Scroll sideways for the rest.

  1. 27.5 Kimi K3.1 Pro
  2. 23.3 Claude Fable 5.2
  3. 17.2 Muse Wonder
  4. 16.1 GPT-6 Astra
  5. 13.9 Muse Spark 1.3
  6. 12.8 Claude Fable 5.1
  7. 12.5 Grok 4.6
  8. 11.4 Claude Sonnet 5.5
  9. 10.8 Claude Opus 5.5
  10. 9.70 Muse Spark 1.1
  11. 9.70 Claude Opus 5
  12. 8.60 Gemini 4 Argon
  13. 5.60 Gemini 3.8 Flash
  1. 1 Kimi K3.1 Pro 27.5%
  2. 2 Claude Fable 5.2 23.3%
  3. 3 Muse Wonder 17.2%
  4. 4 GPT-6 Astra 16.1%
  5. 5 Muse Spark 1.3 13.9%
  6. 6 Claude Fable 5.1 12.8%
  7. 7 Grok 4.6 12.5%
  8. 8 Claude Sonnet 5.5 11.4%
  9. 9 Claude Opus 5.5 10.8%
  10. 10 Muse Spark 1.1 9.70%
  11. 11 Claude Opus 5 9.70%
  12. 12 Gemini 4 Argon 8.60%
  13. 13 Gemini 3.8 Flash 5.60%

Source: Official PharmaBench (micro1) leaderboard

#ModelScoreSettingDateSource
1 Kimi K3.1 Pro 27.5% Oct 2026 Official leaderboard
2 Claude Fable 5.2 23.3% Nov 2026 Official leaderboard
3 Muse Wonder 17.2% Oct 2026 Official leaderboard
4 GPT-6 Astra 16.1% Sep 2026 Official leaderboard
5 Muse Spark 1.3 13.9% Sep 2026 Official leaderboard
6 Claude Fable 5.1 12.8% Sep 2026 Official leaderboard
7 Grok 4.6 12.5% Aug 2026 Official leaderboard
8 Claude Sonnet 5.5 11.4% Sep 2026 Official leaderboard
9 Claude Opus 5.5 10.8% Sep 2026 Official leaderboard
10 Muse Spark 1.1 9.70% Jul 2026 Official leaderboard
11 Claude Opus 5 9.70% Jul 2026 Official leaderboard
12 Gemini 4 Argon 8.60% Sep 2026 Official leaderboard
13 Gemini 3.8 Flash 5.60% Sep 2026 Official leaderboard

3 models have held number one on the official leaderboard since its release in October 2026

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

OpenAI Meta Moonshot AI
Own leaderboard 3 leaders
Kimi K3.1 Pro 27.5%

Source: Official PharmaBench (micro1) leaderboard

Scores over time

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

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Kimi K3.1 Pro Muse Wonder GPT-6 Astra Muse Spark 1.1 0% 20% 40% 60% 80% 100% 2027 Near the ceiling (85%) Kimi K3.1 Pro Muse Wonder

Source: Official PharmaBench (micro1) leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Law, finance and medicine

All 179 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%
  • KBL In use Models answer Korean legal knowledge and reasoning tasks and Korean bar exam questions. It has 7 knowledge tasks, 4 reasoning tasks and 2,510 bar exam items. Solar Pro 4 77.5%
  • 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. Solar Pro 4 93.2%