Leaderboard · LMOD+

Proprietary Open-Source Click a metric header to sort

Model	Release	Anatomical Recognition				Diagnosis Analysis		Staging Acc
Model	Release	Prec.	Rec.	F1	Halluc. Resist.	Binary Acc	Multi-class Acc	Staging Acc
Random Baseline		N/A	N/A	N/A	N/A	0.5000	0.2500	0.2500
GPT-4o	2024-05	0.3116	0.2424	0.2577	0.9786	N/A	N/A	0.1053
LLaVA-Med-v1.5-Mistral-7B	2023-06	0.2090	0.2558	0.2098	0.6240	0.5000	0.2500	0.2368
Yi-VL-6B	2024-05	0.1509	0.0379	0.0451	0.8135	0.4117	0.2525	0.4000
Med-Flamingo		Invalid	Invalid	Invalid	Invalid	Invalid	Invalid	Invalid
InternVL 1.5-2B	2024-05	0.2377	0.2386	0.2204	0.7722	0.5000	0.2525	0.2632
InternVL 1.5-4B	2024-05	0.2499	0.2541	0.2414	0.8096	0.5000	0.2500	0.2500
InternVL 2.0-2B	2024-07	0.3718	0.3912	0.3722	0.9069	0.5000	0.2175	0.2500
InternVL 2.0-4B	2024-07	0.4200	0.4294	0.4096	0.8951	0.5000	0.2525	0.2237
InternVL 2.0-8B	2024-07	0.2865	0.2872	0.2770	0.9533	0.5017	0.3500	0.2500
InternVL 2.5-2B	2024-12	0.3751	0.3681	0.3524	0.9744	0.5017	0.3000	0.2308
InternVL 2.5-4B	2024-12	0.2685	0.1893	0.1890	0.9854	0.5000	0.3225	0.2500
InternVL 2.5-8B	2024-12	0.2851	0.2519	0.2574	0.9864	0.5000	0.3275	0.2500
InternVL 2.5-2B-MPO	2025-04	0.3123	0.2992	0.2835	0.9646	0.5000	0.2375	0.3077
InternVL 2.5-4B-MPO	2025-04	0.3126	0.2261	0.2320	0.9918	0.5000	0.3200	0.2500
InternVL 2.5-8B-MPO	2025-04	0.2986	0.2536	0.2624	0.9838	0.5000	0.2650	0.1053
LLaVA-1.5-7B	2023-10	0.0965	0.0530	0.0557	0.4629	0.4937	0.2475	0.2500
LLaVA-Mistral-7B	2024-01	0.0806	0.0773	0.0696	0.5788	0.5000	0.2500	0.2500
LLaVA-Vicuna-7B	2024-01	0.0437	0.0353	0.0342	0.1929	0.5000	0.3693	N/A
LLaVA-Vicuna-13B	2024-01	0.1123	0.0071	0.0105	0.6612	0.5000	0.2725	N/A
Qwen-VL-Chat	2023-08	0.1040	0.0120	0.0178	0.7790	0.5000	0.2675	0.2763
Qwen-3B		0.2611	0.1489	0.1509	0.7468	0.5000	0.2500	0.2368
Qwen-7B	2023-08	0.2506	0.2261	0.2251	0.7556	0.5017	0.2500	0.2368
DeepSeek VL2-Tiny	2024-12	0.2228	0.0583	0.0688	0.9518	0.5000	0.2500	0.2237
DeepSeek VL2-Small	2024-12	0.0805	0.0130	0.0218	0.5917	Invalid	0.1700	0.0667

Comprehensive zero-shot evaluation across anatomical recognition, diagnosis, and stage classification. The best result in each column is bold, the second best is underlined. All models use consistent prompt templates.

Submit your model. To appear on this leaderboard, send the scores and a brief description of your multimodal model to Zhenyue Qin at zhenyue.qin@yale.edu.