67AI Lab L3 nuclear medicine guideline questions
Models answer questions using eight retrieved passages from nuclear medicine guidelines. They must abstain when the passages lack an answer.
The lab compares seven models on 120 answerable and 30 unanswerable questions. Three agents wrote the questions, followed by a separate review.
- Made by
- 67AI Lab
- Released
- November 2026
- Kind
- Medicine
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Measures
- Capability
- Subject
- Clinical medicine
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use, Generated
- Refresh
- One fixed set
- Run by
- A host
- In views
- Biology and medicine
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5.5 leads with 90.8% among models released by September 2026 Claude Opus 5.5 leads with 90.8% among models released by September 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 September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Sol
- and 15 more
- 1 Claude Opus 5.5 90.8%
- 2
DeepSeek V4.1 Flash 90%
- 3
Qwen 3.8 27B 81.7%
- 4
Qwen3-Coder-Next 80%
- 5
Gemma 4 26B A4B 79.2%
- 6
Qwen 3.6 35B-A3B 75.8%
- 7 Nemotron 3.5 30B-A3B 71.7%
Source: Official 67AI Lab L3 nuclear medicine guideline questions leaderboard
- 1 Claude Opus 5.5 90.8%
- 2
DeepSeek V4.1 Flash 90%
- 3
Qwen 3.8 27B 81.7%
- 4
Qwen3-Coder-Next 80%
- 5
Gemma 4 26B A4B 79.2%
- 6
Qwen 3.6 35B-A3B 75.8%
Source: Official 67AI Lab L3 nuclear medicine guideline questions leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 90.8% | Sep 2026 | Official leaderboard | |
| 2 | | 90% | Sep 2026 | Official leaderboard | |
| 3 | | 81.7% | Aug 2026 | Official leaderboard | |
| 4 | | 80% | Feb 2026 | Official leaderboard | |
| 5 | | 79.2% | Apr 2026 | Official leaderboard | |
| 6 | | 75.8% | Apr 2026 | Official leaderboard | |
| 7 | Nemotron 3.5 30B-A3B | 71.7% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 90.8% | Sep 2026 | Official leaderboard | |
| 2 | | 90% | Sep 2026 | Official leaderboard | |
| 3 | | 81.7% | Aug 2026 | Official leaderboard | |
| 4 | | 80% | Feb 2026 | Official leaderboard | |
| 5 | | 79.2% | Apr 2026 | Official leaderboard | |
| 6 | | 75.8% | Apr 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Correct when right passage retrieved and Correct abstention. Each ranks models on one part of the test. Claude Opus 5.5 leads Correct when right passage retrieved and Gemma 4 26B A4B leads Correct abstention. Arrows show how far a model moved from its overall rank among the models we track.
Correct when right passage retrieved
6 models we track have a score here.
- 1 Claude Opus 5.5 98.2%
- 2
DeepSeek V4.1 Flash 96.4%
- 3
Qwen 3.8 27B 88.2%
- 4
Gemma 4 26B A4B ↑1 86.4%
- 5
Qwen3-Coder-Next ↓1 85.5%
- 6
Qwen 3.6 35B-A3B 81.8%
Correct abstention
6 models we track have a score here.
- 1
Gemma 4 26B A4B ↑4 100%
- 2
Qwen 3.6 35B-A3B ↑4 100%
- 3
Qwen 3.8 27B 100%
- 4
DeepSeek V4.1 Flash ↓2 100%
- 5 Claude Opus 5.5 ↓4 100%
- 6
Qwen3-Coder-Next ↓2 96.7%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official 67AI Lab L3 nuclear medicine guideline questions leaderboard
DeepSeek V4.1 Flash on the official leaderboard passed 85% in September 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official 67AI Lab L3 nuclear medicine guideline questions 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
- 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 Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 6 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Note Frontier models 1 of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5.5 (#5).
- Note Headroom Saturated. The best is 90.8%, past 85% since September 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on 67ailab.com: 6 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.