Benchmark Almanac

DiagTrace

Kimi K2.5 0.40 leads since November 2026
Not in model cards

Models request information about a patient one turn at a time. The evaluator compares the sequence of requests with the published case history.

Made by
Yufan Wang and colleagues
Released
November 2026
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Multi-turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Kimi K2.5 #76 on the capability index
Last model added
January 2026
Scores refreshed
November 20th, 2026
4
Models scored on its own leaderboard

Kimi K2.5 leads with 0.40 among models released by January 2026

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. The first metric in the corrected Table 3 is Tversky alignment on 225 matched cases. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in January 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 Kimi K2.5 0.40
  2. 2 GPT-4.1 mini 0.36
  3. 3 Gemini 2.5 Flash Sep 2025 0.36
  4. 4 Claude Haiku 4.5 0.33

Source: Official DiagTrace leaderboard

#ModelScoreSettingDateSource
1 Kimi K2.5 0.40 Jan 2026 Official leaderboard
2 GPT-4.1 mini 0.36 Apr 2025 Official leaderboard
3 Gemini 2.5 Flash Sep 2025 0.36 Sep 2025 Official leaderboard
4 Claude Haiku 4.5 0.33 Oct 2025 Official leaderboard

Rankings by part

We read 9 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as admission or clinical course, imaging and lab tests. Kimi K2.5 leads 6 of them, and Gemini 2.5 Flash leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.

admission or clinical course

Fraction of cases with a matching request among cases containing this category. 4 models we track have a score here.

  1. 1 Kimi K2.5 0.93
  2. 2 Claude Haiku 4.5 ↑2 0.87
  3. 3 GPT-4.1 mini ↓1 0.42
  4. 4 Gemini 2.5 Flash Sep 2025 ↓1 0.30

Number one over time

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

Moonshot AI
Own leaderboard 1 leader
Kimi K2.5 0.40

Source: Official DiagTrace 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
0.34 0.36 0.38 0.40 2025 2026 0.34 0.36 0.38 0.40 2025 2026

Source: Official DiagTrace 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

7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 10 months ago, in January 2026, for Kimi K2.5. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (4 entries).
  • Note Models scored Only 4 models we track.
  • Warning Newest score The newest came 10 months ago, in January 2026, for Kimi K2.5.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Kimi K2.5 (#76).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 4 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