Benchmark Almanac

Mitosis Bench

Gemini 4 Argon 32.4% leads since October 2026
Not in model cards

Agents mark every dividing cell in a tumor image. Each mark must fall within 30 pixels of an expert label. The grader rejects extra or missing marks.

On October 18, 2026, Gemini 4 Argon led with 32.4% pass@1 on 100 tasks. Claude Opus 5.5, GPT-6 Astra, GLM 5.3 Flash and DeepSeek V4.1 Flash also ran.

Made by
Dylan Tirandaz
Released
October 2026
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Actions
Interaction
Agentic
Environment
Desktop apps
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
5
Models scored on its own leaderboard

Gemini 4 Argon leads with 32.4% among models released by September 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 4 Argon 32.4%
  2. 2 Claude Opus 5.5 28.6%
  3. 3 GPT-6 Astra 22.8%
  4. 4 GLM-5.3-Flash 16.8%
  5. 5 DeepSeek V4.1 Flash 8.80%

Source: Official Mitosis Bench leaderboard

#ModelScoreSettingDateSource
1 Gemini 4 Argon 32.4% Sep 2026 Official leaderboard
2 Claude Opus 5.5 28.6% Sep 2026 Official leaderboard
3 GPT-6 Astra 22.8% Sep 2026 Official leaderboard
4 GLM-5.3-Flash 16.8% Aug 2026 Official leaderboard
5 DeepSeek V4.1 Flash 8.80% Sep 2026 Official leaderboard

Number one over time

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

Google DeepMind
Own leaderboard Not tested since Oct 2026

Source: Official Mitosis Bench leaderboard

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
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% Near the ceiling (85%) Gemini 4 Argon GPT-6 Astra GLM-5.3-Flash 0% 20% 40% 60% 80% 100% Near the ceiling (85%) Gemini 4 Argon GPT-6 Astra

Source: Official Mitosis Bench 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 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (5 entries).
  • Pass Models scored 5 models we track.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Pass Frontier models 3 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Pass Headroom The best is 32.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on dylantirandaz.com: 5 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