Benchmark Almanac

RSNA Knee AUC10

GPT-6.1 Sol 0.92 leads since October 2026
Not in model cards

Models label twelve knee findings from images, radiology reports, or both. The grader measures how well their predictions distinguish findings on ten reference studies.

Kaggle publishes scores for 29 distinct model versions.

Made by
Kirderf
Released
October 2026
Kind
Medicine
Level
Expert
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
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
29
Entries on its own leaderboard, 27 models we track

GPT-6.1 Sol leads with 0.92 among models released by September 2026 GPT-6.1 Sol leads with 0.92 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:

  1. 1 GPT-6.1 Sol 0.92
  2. 2 GLM-5 0.90
  3. 3 GPT-6 Astra 0.82
  4. 4 GPT-5.5 0.82
  5. 5 Gemini 4 Argon 0.80
  6. 6 Gemma 4 31B IT 0.79
  7. 7 Claude Sonnet 5.5 0.79
  8. 8 Gemini 3.1 Flash-Lite 0.79
  9. 9 Gemini 3.1 Pro 0.78
  10. 10 Gemini 3.8 Flash 0.78
  11. 11 GPT-5.6 Sol 0.75
  12. 12 Gemini 2.5 Pro Jun 2025 0.74
  13. 13 Gemma 4 26B A4B 0.73
  14. 14 GPT-5.6 Terra 0.71
  15. 15 GPT-5.6 Luna 0.71
  16. 16 Claude Haiku 4.5 0.70
  17. 17 Claude Opus 5.5 0.67
  18. 18 GPT-6 Luna 0.66
  19. 19 GPT-5.4 0.63
  20. 20 GPT-5.4 Mini 0.60
  21. 21 Qwen 3 Next 80B Instruct 0.52
  22. 22 Qwen3-Coder-480B-A35B 0.51
  23. 23 Claude Sonnet 5 0.51
  24. 24 Qwen 3 235B A22B Instruct 2506 0.50
  25. 25 gpt-oss-120b 0.50
  26. 26 gpt-oss-20b 0.49
  27. 27 GPT-5.4 Nano 0.48
  28. 28 Claude Sonnet 4.6 0.44
  29. 29 Claude Opus 5 0.43

Source: Official RSNA Knee AUC10 leaderboard

#EntryScoreSettingReleasedRun onSource
1 GPT-6.1 Sol 0.92 Sep 2026 Oct 2026 Official leaderboard
2 GLM-5 0.90 Feb 2026 Oct 2026 Official leaderboard
3 GPT-6 Astra 0.82 Sep 2026 Oct 2026 Official leaderboard
4 GPT-5.5 0.82 Apr 2026 Oct 2026 Official leaderboard
5 Gemini 4 Argon 0.80 Sep 2026 Oct 2026 Official leaderboard
6 Gemma 4 31B IT 0.79 Apr 2026 Oct 2026 Official leaderboard
7 Claude Sonnet 5.5 0.79 Sep 2026 Oct 2026 Official leaderboard
8 Gemini 3.1 Flash-Lite 0.79 Mar 2026 Oct 2026 Official leaderboard
9 Gemini 3.1 Pro 0.78 Feb 2026 Oct 2026 Official leaderboard
10 Gemini 3.8 Flash 0.78 Sep 2026 Oct 2026 Official leaderboard
11 GPT-5.6 Sol 0.75 Jul 2026 Oct 2026 Official leaderboard
12 Gemini 2.5 Pro Jun 2025 0.74 Jun 2025 Oct 2026 Official leaderboard
13 Gemma 4 26B A4B 0.73 Apr 2026 Oct 2026 Official leaderboard
14 GPT-5.6 Terra 0.71 Jul 2026 Oct 2026 Official leaderboard
15 GPT-5.6 Luna 0.71 Jul 2026 Oct 2026 Official leaderboard
16 Claude Haiku 4.5 0.70 Oct 2025 Oct 2026 Official leaderboard
17 Claude Opus 5.5 0.67 Sep 2026 Oct 2026 Official leaderboard
18 GPT-6 Luna 0.66 Sep 2026 Oct 2026 Official leaderboard
19 GPT-5.4 0.63 Mar 2026 Oct 2026 Official leaderboard
20 GPT-5.4 Mini 0.60 Mar 2026 Oct 2026 Official leaderboard
21 Qwen 3 Next 80B Instruct 0.52 Oct 2026 Official leaderboard
22 Qwen3-Coder-480B-A35B 0.51 Jul 2025 Oct 2026 Official leaderboard
23 Claude Sonnet 5 0.51 Jun 2026 Oct 2026 Official leaderboard
24 Qwen 3 235B A22B Instruct 2506 0.50 Oct 2026 Official leaderboard
25 gpt-oss-120b 0.50 Aug 2025 Oct 2026 Official leaderboard
26 gpt-oss-20b 0.49 Aug 2025 Oct 2026 Official leaderboard
27 GPT-5.4 Nano 0.48 Mar 2026 Oct 2026 Official leaderboard
28 Claude Sonnet 4.6 0.44 Feb 2026 Oct 2026 Official leaderboard
29 Claude Opus 5 0.43 Jul 2026 Oct 2026 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 GPT-6.1 Sol 0.92 Sep 2026 Oct 2026 Official leaderboard
2 GLM-5 0.90 Feb 2026 Oct 2026 Official leaderboard
3 GPT-6 Astra 0.82 Sep 2026 Oct 2026 Official leaderboard
4 GPT-5.5 0.82 Apr 2026 Oct 2026 Official leaderboard
5 Gemini 4 Argon 0.80 Sep 2026 Oct 2026 Official leaderboard
6 Gemma 4 31B IT 0.79 Apr 2026 Oct 2026 Official leaderboard
7 Claude Sonnet 5.5 0.79 Sep 2026 Oct 2026 Official leaderboard
8 Gemini 3.1 Flash-Lite 0.79 Mar 2026 Oct 2026 Official leaderboard
9 Gemini 3.1 Pro 0.78 Feb 2026 Oct 2026 Official leaderboard
10 Gemini 3.8 Flash 0.78 Sep 2026 Oct 2026 Official leaderboard
11 GPT-5.6 Sol 0.75 Jul 2026 Oct 2026 Official leaderboard
12 Gemini 2.5 Pro Jun 2025 0.74 Jun 2025 Oct 2026 Official leaderboard
13 Gemma 4 26B A4B 0.73 Apr 2026 Oct 2026 Official leaderboard
14 GPT-5.6 Terra 0.71 Jul 2026 Oct 2026 Official leaderboard
15 GPT-5.6 Luna 0.71 Jul 2026 Oct 2026 Official leaderboard
16 Claude Haiku 4.5 0.70 Oct 2025 Oct 2026 Official leaderboard
17 Claude Opus 5.5 0.67 Sep 2026 Oct 2026 Official leaderboard
18 GPT-6 Luna 0.66 Sep 2026 Oct 2026 Official leaderboard
19 GPT-5.4 0.63 Mar 2026 Oct 2026 Official leaderboard
20 GPT-5.4 Mini 0.60 Mar 2026 Oct 2026 Official leaderboard
21 Qwen3-Coder-480B-A35B 0.51 Jul 2025 Oct 2026 Official leaderboard
22 Claude Sonnet 5 0.51 Jun 2026 Oct 2026 Official leaderboard
23 gpt-oss-120b 0.50 Aug 2025 Oct 2026 Official leaderboard
24 gpt-oss-20b 0.49 Aug 2025 Oct 2026 Official leaderboard
25 GPT-5.4 Nano 0.48 Mar 2026 Oct 2026 Official leaderboard
26 Claude Sonnet 4.6 0.44 Feb 2026 Oct 2026 Official leaderboard
27 Claude Opus 5 0.43 Jul 2026 Oct 2026 Official leaderboard

Number one over time

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

OpenAI
Own leaderboard Not tested since Oct 2026

Source: Official RSNA Knee AUC10 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
0.40 0.60 0.80 1.00 2025 2026 0.40 0.60 0.80 1.00 2025 2026

Source: Official RSNA Knee AUC10 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 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (29 entries).
  • Pass Models scored 27 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on kaggle.com: 27 rows for models we track and 2 other entries 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