OCT-Bench
Models answer 10,076 questions about retinal scans, from anatomy to treatment and prognosis. The evaluator measures answer accuracy and counts invalid responses as incorrect.
Questions cover 20 tasks over 4,137 optical coherence tomography images. The scope includes clinical reasoning beyond image classification.
- Made by
- Shandong University, Joint SDU-NTU Centre for Artificial Intelligence Research, and collaborators
- Released
- July 2026
- Kind
- Medicine
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Clinical medicine
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Biology and medicine
- Strongest model tested
- GPT-5.4 Mini #74 on the capability index
- Last model added
- March 2026
- Scores refreshed
- November 18th, 2026
In the authors’ words
Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although multimodal large language models (MLLMs) have demonstrated considerable potential in medical image analysis, existing benchmarks largely reduce OCT understanding to coarse-grained disease classification or isolated visual question answering, leaving the complete cognitive process from visual perception to clinical reasoning insufficiently evaluated. To address this limitation, we introduce OCT-Bench, a comprehensive benchmark dedicated to OCT image understanding. OCT-Bench comprises 10,076 high-quality multiple-choice questions constructed from 4,137 OCT images across seven public datasets. Following the real-world clinical interpretation workflow, we establish a hierarchical capability taxonomy consisting of 20 fine-grained tasks across three dimensions: Perception, Cognition, and Reasoning. These tasks cover a broad range of capabilities, including imaging attributes, retinal anatomy, lesion characteristics, spatial relationships, disease assessment, therapeutic decision-making, and prognostic management. We systematically evaluate 20 representative MLLMs, including proprietary models, open-source general-purpose models, and medical-domain models. Experimental results demonstrate that current models remain substantially short of reliable OCT understanding. Moreover, neither medical-domain adaptation nor increased model scale consistently improves performance across capability levels. OCT-Bench enables comprehensive and fine-grained evaluation of MLLMs, providing a foundation for identifying capability bottlenecks and advancing clinically grounded OCT understanding.
GPT-5.4 Mini leads with 62% among models released by March 2026 GPT-5.4 Mini leads with 62% among models released by March 2026
Best score per entry from the benchmark's paper, read on November 18th, 2026. A paper’s table doesn’t add newer models. 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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 62.0 GPT-5.4 Mini
- 60.5
Gemini 2.5 Flash
- 58.4 Hulu-Med-32B
- 56.6 Lingshu-32B
- 55.6 HealthGPT-Pro-8B
- 54.5
InternVL2.5-26B
- 54.1 Hulu-Med-7B
- 53.6 Fleming-VL-8B
- 52.4
Qwen2.5-VL-32B
- 52.4 Grok 4 Fast
- 51.7 MediX-R1-8B
- 51.5 Lingshu-7B
- 50.5 LLaVA-1.6-34B
- 49.5
Qwen2.5-VL-7B
- 46.6
InternVL2.5-4B
- 45.1 HealthGPT-M3
- 44.7
Gemma 3 12B
- 42.2 MedGemma-4B
- 42.0 Phi-3-Vision-128k
- 39.6
LLaVA-v1.5-13B
- 1 GPT-5.4 Mini 62%
- 2
Gemini 2.5 Flash Sep 2025 60.5%
- 3 Hulu-Med-32B 58.4%
- 4 Lingshu-32B 56.6%
- 5 HealthGPT-Pro-8B 55.6%
- 6
InternVL2.5-26B 54.5%
- 7 Hulu-Med-7B 54.1%
- 8 Fleming-VL-8B 53.6%
- 9
Qwen2.5-VL-32B 52.4%
- 10 Grok 4 Fast 52.4%
- 11 MediX-R1-8B 51.7%
- 12 Lingshu-7B 51.5%
- 13 LLaVA-1.6-34B 50.5%
- 14
Qwen2.5-VL-7B 49.5%
- 15
InternVL2.5-4B 46.6%
- 16 HealthGPT-M3 45.1%
- 17
Gemma 3 12B 44.7%
- 18 MedGemma-4B 42.2%
- 19 Phi-3-Vision-128k 42%
- 20
LLaVA-v1.5-13B 39.6%
Source: The OCT-Bench paper
- 1 GPT-5.4 Mini 62%
- 2
Gemini 2.5 Flash Sep 2025 60.5%
- 3
InternVL2.5-26B 54.5%
- 4
Qwen2.5-VL-32B 52.4%
- 5 Grok 4 Fast 52.4%
- 6
Qwen2.5-VL-7B 49.5%
- 7
InternVL2.5-4B 46.6%
- 8
Gemma 3 12B 44.7%
- 9
LLaVA-v1.5-13B 39.6%
Source: The OCT-Bench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 Mini | 62% | Mar 2026 | Official leaderboard | |
| 2 | | 60.5% | Sep 2025 | Official leaderboard | |
| 3 | Hulu-Med-32B | 58.4% | Official leaderboard | ||
| 4 | Lingshu-32B | 56.6% | Official leaderboard | ||
| 5 | HealthGPT-Pro-8B | 55.6% | Official leaderboard | ||
| 6 | | 54.5% | Dec 2024 | Official leaderboard | |
| 7 | Hulu-Med-7B | 54.1% | Official leaderboard | ||
| 8 | Fleming-VL-8B | 53.6% | Official leaderboard | ||
| 9 | | 52.4% | Mar 2025 | Official leaderboard | |
| 10 | Grok 4 Fast | 52.4% | Sep 2025 | Official leaderboard | |
| 11 | MediX-R1-8B | 51.7% | Official leaderboard | ||
| 12 | Lingshu-7B | 51.5% | Official leaderboard | ||
| 13 | LLaVA-1.6-34B | 50.5% | Official leaderboard | ||
| 14 | | 49.5% | Jan 2025 | Official leaderboard | |
| 15 | | 46.6% | Dec 2024 | Official leaderboard | |
| 16 | HealthGPT-M3 | 45.1% | Official leaderboard | ||
| 17 | | 44.7% | Mar 2025 | Official leaderboard | |
| 18 | MedGemma-4B | 42.2% | Official leaderboard | ||
| 19 | Phi-3-Vision-128k | 42% | Official leaderboard | ||
| 20 | | 39.6% | Oct 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 Mini | 62% | Mar 2026 | Official leaderboard | |
| 2 | | 60.5% | Sep 2025 | Official leaderboard | |
| 3 | | 54.5% | Dec 2024 | Official leaderboard | |
| 4 | | 52.4% | Mar 2025 | Official leaderboard | |
| 5 | Grok 4 Fast | 52.4% | Sep 2025 | Official leaderboard | |
| 6 | | 49.5% | Jan 2025 | Official leaderboard | |
| 7 | | 46.6% | Dec 2024 | Official leaderboard | |
| 8 | | 44.7% | Mar 2025 | Official leaderboard | |
| 9 | | 39.6% | Oct 2023 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s paper: Perception, Cognition and Reasoning. Each ranks models on one part of the test. GPT-5.4 Mini leads 2 of them, and Gemini 2.5 Flash leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Perception
9 models we track have a score here.
- 1 GPT-5.4 Mini 75.8%
- 2
InternVL2.5-26B ↑1 72.5%
- 3
Gemini 2.5 Flash Sep 2025 ↓1 67.7%
- 4
Qwen2.5-VL-7B ↑2 66.7%
- 5
Qwen2.5-VL-32B ↓1 66%
- 6 Grok 4 Fast ↓1 63.5%
- 7
Gemma 3 12B ↑1 62.6%
- 8
InternVL2.5-4B ↓1 61.2%
- 9
LLaVA-v1.5-13B 54.2%
Cognition
9 models we track have a score here.
- 1
Gemini 2.5 Flash Sep 2025 ↑1 64.2%
- 2 GPT-5.4 Mini ↓1 60%
- 3 Grok 4 Fast ↑2 51.4%
- 4
InternVL2.5-26B ↓1 49.4%
- 5
Qwen2.5-VL-32B ↓1 48.6%
- 6
Qwen2.5-VL-7B 42.7%
- 7
InternVL2.5-4B 42.3%
- 8
Gemma 3 12B 36.6%
- 9
LLaVA-v1.5-13B 28.8%
Reasoning
9 models we track have a score here.
- 1 GPT-5.4 Mini 38.5%
- 2
Gemini 2.5 Flash Sep 2025 38.4%
- 3
Qwen2.5-VL-32B ↑1 33%
- 4 Grok 4 Fast ↑1 32.2%
- 5
LLaVA-v1.5-13B ↑4 32.1%
- 6
InternVL2.5-26B ↓3 29.1%
- 7
Qwen2.5-VL-7B ↓1 28.6%
- 8
InternVL2.5-4B ↓1 26.2%
- 9
Gemma 3 12B ↓1 25.3%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The OCT-Bench paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official OCT-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
- 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
9 of 10 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 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (20 entries).
- Pass Models scored 9 models we track, plus 11 other entries 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 Mini (#74).
- Pass Headroom The best is 62%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 9 rows for models we track and 11 other entries at the last read.
- Pass Last read November 18th, 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.