Benchmark Almanac

Medical Chronology LLM Benchmark

Claude Opus 4.6 88.9 leads since April 2026
Not in model cards

Models extract medical timelines from six synthetic document sets in three independent rounds. Checks compare extracted events with reference timelines and assess semantic fidelity, formatting, date order, and hallucinations. A weighted composite combines these checks with ROUGE and extraction F1.

Extraction F1 contributes 30%, semantic fidelity and hallucination each 20%, and formatting, chronology, and ROUGE each 10%. Hallucination checking uses majority votes from three model judges. Six synthetic cases do not establish performance on clinical records. The release date follows the public dataset creation date.

Made by
Superinsight, Inc.
Released
April 2026
Kind
Medicine
Level
Expert
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Documents → Text
Interaction
Single turn
Items from
Generated
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-5.4 Pro #19 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
11
Entries on its own leaderboard, 10 models we track

Claude Opus 4.6 leads with 88.9 among models released by March 2026 Claude Opus 4.6 leads with 88.9 among models released by March 2026

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 March 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 Claude Opus 4.6 88.9
  2. 2 Claude Opus 4.5 87.7
  3. 3 Gemini 2.5 Flash Sep 2025 87.3
  4. 4 GPT-5.4 87.1
  5. 5 GPT-5.4 Mini 86.9
  6. 6 Gemini 3 Flash 86.6
  7. 7 GPT-5.4 Pro 86.6
  8. 8 qwen3-235b Nebius FP16 85.9
  9. 9 Gemini 2.5 Pro Jun 2025 85.7
  10. 10 MiniMax-M2.5 Nebius FP4 85.6
  11. 11 Gemini 3.1 Pro 84.7

Source: Official Medical Chronology LLM Benchmark leaderboard

#EntryScoreSettingDateSource
1 Claude Opus 4.6 88.9 Feb 2026 Official leaderboard
2 Claude Opus 4.5 87.7 Nov 2025 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 87.3 Sep 2025 Official leaderboard
4 GPT-5.4 87.1 Mar 2026 Official leaderboard
5 GPT-5.4 Mini 86.9 Mar 2026 Official leaderboard
6 Gemini 3 Flash 86.6 Dec 2025 Official leaderboard
7 GPT-5.4 Pro 86.6 Mar 2026 Official leaderboard
8 qwen3-235b 85.9 Nebius FP16 Official leaderboard
9 Gemini 2.5 Pro Jun 2025 85.7 Jun 2025 Official leaderboard
10 MiniMax-M2.5 85.6 Nebius FP4 Feb 2026 Official leaderboard
11 Gemini 3.1 Pro 84.7 Feb 2026 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 4.6 88.9 Feb 2026 Official leaderboard
2 Claude Opus 4.5 87.7 Nov 2025 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 87.3 Sep 2025 Official leaderboard
4 GPT-5.4 87.1 Mar 2026 Official leaderboard
5 GPT-5.4 Mini 86.9 Mar 2026 Official leaderboard
6 Gemini 3 Flash 86.6 Dec 2025 Official leaderboard
7 GPT-5.4 Pro 86.6 Mar 2026 Official leaderboard
8 Gemini 2.5 Pro Jun 2025 85.7 Jun 2025 Official leaderboard
9 MiniMax-M2.5 85.6 Nebius FP4 Feb 2026 Official leaderboard
10 Gemini 3.1 Pro 84.7 Feb 2026 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Semantic, F1 and Formatting. GPT-5.4 leads 1 of them, and 5 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Semantic

10 models we track have a score here.

  1. 1 GPT-5.4 ↑3 78.9
  2. 2 GPT-5.4 Pro ↑5 78.1
  3. 3 Claude Opus 4.6 ↓2 75.4
  4. 4 Claude Opus 4.5 ↓2 74.2
  5. 5 GPT-5.4 Mini 72.1
  6. 6 Gemini 2.5 Flash Sep 2025 ↓3 71.9
  7. 7 Gemini 3 Flash ↓1 70.7
  8. 8 Gemini 3.1 Pro ↑2 70.7
  9. 9 MiniMax-M2.5 70.2
  10. 10 Gemini 2.5 Pro Jun 2025 ↓2 69.2

Number one over time

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

Anthropic
Own leaderboard Not tested since Apr 2026

Source: Official Medical Chronology LLM Benchmark 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
84.0 85.0 86.0 87.0 88.0 89.0 2025 2026 84.0 85.0 86.0 87.0 88.0 89.0 2025 2026

Source: Official Medical Chronology LLM Benchmark 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 8 months ago, in March 2026, for GPT-5.4 Mini. 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 official leaderboard (11 entries).
  • Pass Models scored 10 models we track, plus 1 other entry on its leaderboard.
  • Warning Newest score The newest came 8 months ago, in March 2026, for GPT-5.4 Mini.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 Pro (#19).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 10 rows for models we track and 1 other entry 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