Our new X account is live! Follow @wizwand_team for updates

Multimodal Capability Evaluation on MM-Vet

85.6Score

Masters

Updated 2d ago

Evaluation Results

Method
Masters 2025.12	85.6	-	-	-	-	-	-
Masters 2025.12	83.8	-	-	-	-	-	-
Gemini-2.5-Pro 2025.12	83.3	-	-	-	-	-	-
InternVL3.5-38B 2025.12	82.2	-	-	-	-	-	-
Masters 2025.12	81.7	-	-	-	-	-	-
InternVL3-78B 2025.12	81.3	-	-	-	-	-	-
Qwen3-VL-32B 2025.12	79.4	-	-	-	-	-	-
Masters 2025.12	79.4	-	-	-	-	-	-
GPT-4.1 2025.12	78.8	-	-	-	-	-	-
GPT-5 2025.12	77.6	-	-	-	-	-	-
Qwen2.5-VL-72B 2025.12	76.9	-	-	-	-	-	-
GLM-4.5V 2025.12	75.2	-	-	-	-	-	-
GPT-4o-20240806 2024.10	75.1	-	-	-	-	-	-
Gemini-2.0-Flash 2025.12	73.6	-	-	-	-	-	-
Qwen-VL-Max-0809 2024.10	72.3	-	-	-	-	-	-
InternVL3.5 2025.12	71.7	-	-	-	-	-	-
Claude-3.5-Sonnet 2025.12	70.1	-	-	-	-	-	-
Claude-3.7-Sonnet 2025.12	70	-	-	-	-	-	-
GPT-4o 2025.12	69.1	-	-	-	-	-	-
SAIL-VL2 2025.12	68.7	-	-	-	-	-	-
Claude3.5-Sonnet 2024.10	66	-	-	-	-	-	-
RecursiveVLM 2026.02	65.64	-	-	-	-	-	-
InternVL2-Llama3-76B 2024.10	64.4	-	-	-	-	-	-
RecursiveVLM 2026.02	64.04	-	-	-	-	-	-
Gemini-1.5-Pro 2024.10	64	-	-	-	-	-	-
Gemini-1.5-Pro 2025.12	64	-	-	-	-	-	-
Standard Transformer 2026.02	63.26	-	-	-	-	-	-
InternVL3 2025.12	62.2	-	-	-	-	-	-
Qwen2-VL 2024.11	62	-	-	-	-	-	-
SAIL-VL1.5 2025.12	61.4	-	-	-	-	-	-
Molmo-72B 2025.12	61.1	-	-	-	-	-	-
LLaVA-OneVision-72B 2025.12	60.6	-	-	-	-	-	-
RecursiveVLM 2026.02	59.95	-	-	-	-	-	-
RecursiveVLM 2026.02	59.82	-	-	-	-	-	-
HyperVL ViTL 2025.12	59	-	-	-	-	-	-
NVLM-72B 2025.12	58.9	-	-	-	-	-	-
Gemini-1.0-Pro 2024.10	58.6	-	-	-	-	-	-
Meteor 2024.05	57.3	-	-	-	-	-	-
HyperVL 2025.12	56.3	-	-	-	-	-	-
Qwen-VL-Plus 2024.10	55.7	-	-	-	-	-	-
Standard Transformer 2026.02	55.28	-	-	-	-	-	-
LLAVA-NeXT 2024.11	54.8	-	-	-	-	-	-
TroL-7B 2024.06	54.7	-	-	-	-	-	-
InternVL2-8B + RP 2024.08	52.6	-	-	-	-	-	-
AndesVL 2025.12	52	-	-	-	-	-	-
Claude3-Sonnet 2024.10	51.7	-	-	-	-	-	-
LongVILA-7B (S3) 2024.08	51.7	-	-	-	-	-	-
Qwen2-VL-2B 2024.10	51.5	-	-	-	-	-	-
Vanilla recursion 2026.02	51.24	-	-	-	-	-	-
Vanilla recursion w/ RMSNorm 2026.02	51.01	-	-	-	-	-	-
MiniGemini-HD-13B 2024.06	50.5	-	-	-	-	-	-
Vanilla recursion 2026.02	49.82	-	-	-	-	-	-
M3ID 2026.02	49.72	46.56	41.55	44.88	46	34.62	50.73
Qwen2-VL 2025.12	49.5	-	-	-	-	-	-
InternVL2-8B-FT 2024.08	49.2	-	-	-	-	-	-
GPT-4v (1106, detail-high) 2024.10	49	-	-	-	-	-	-
SPHINX-Plus-13B 2024.06	47.9	-	-	-	-	-	-
Vanilla recursion w/ RMSNorm 2026.02	47.8	-	-	-	-	-	-
REVIS 2026.02	47.48	43.85	40.71	43	39.47	34.62	48.6
Qwen-VL-Chat-7B 2024.06	47.3	-	-	-	-	-	-
LLaVA-NeXT-13B 2024.06	47.3	-	-	-	-	-	-
VCD 2026.02	47.16	40.31	41.94	53.8	38.8	19.23	50.47
Regular 2026.02	46.97	42.29	41.79	44.12	40.53	25	49
Only 2026.02	46.97	39.58	42.74	45.13	37.2	25	49.93
AGLA 2026.02	46.88	41.25	40.48	44	39.47	25	49.53
MM1-MoE-7Bx32 2024.06	45.2	-	-	-	-	-	-
SETOKIM 2024.06	45.2	-	-	-	-	-	-
LLaVA-v1.6 (7B) w/ STIC 2024.05	45	-	-	-	-	-	-
H2OVL-Mississippi-2B 2024.10	44.7	-	-	-	-	-	-
Ovis2 2025.12	44.4	-	-	-	-	-	-
Phi-3-Vision 2024.10	44.1	-	-	-	-	-	-
MGM-7B + RP 2024.08	44.1	-	-	-	-	-	-
LLaVA-NeXT-7B 2024.06	43.9	-	-	-	-	-	-
LLaVA-NeXT 2024.12	43.9	-	-	-	-	-	-
VTI 2026.02	43.44	36.25	40.12	42.88	35.73	15.77	46.73
Qwen3-VL 2025.12	43.3	-	-	-	-	-	-
LLaVA-v1.6 (7B) 2024.05	42.2	-	-	-	-	-	-
MM1-7B 2024.06	42.1	-	-	-	-	-	-
ASMv2 2024.02	41.3	-	-	-	-	-	-
MiniGemini-HD-7B 2024.06	41.3	-	-	-	-	-	-
Mini-Gemini-HD 2024.11	41.3	-	-	-	-	-	-
FocusLLaVA 2024.11	41.3	-	-	-	-	-	-
MiniCPM-V-2 2024.10	41	-	-	-	-	-	-
SPHINX-MoE-7Bx8 2024.06	40.9	-	-	-	-	-	-
MGM-7B 2024.08	40.8	-	-	-	-	-	-
LLaVA-NeXT 2024.11	40.6	-	-	-	-	-	-
SPHINX-7B 2024.06	40.2	-	-	-	-	-	-
mPlug-Owl3 2024.11	40.1	-	-	-	-	-	-
MiniMonkey 2024.10	39.8	-	-	-	-	-	-
InternVL2-2B 2024.10	39.7	-	-	-	-	-	-
VILA 2024.02	38.8	-	-	-	-	-	-
VILA-13B 2024.06	38.8	-	-	-	-	-	-
VILA 2024.08	38.8	-	-	-	-	-	-
SIMA 2024.05	38.4	-	-	-	-	-	-
SIMA 2024.05	38.3	-	-	-	-	-	-
Qwen-VL 2024.06	38.2	-	-	-	-	-	-
PreSel 2025.03	37.7	-	-	-	-	-	-
ShareGPT4V-7B 2024.06	37.6	-	-	-	-	-	-
ShareGPT4V 2024.12	37.6	-	-	-	-	-	-
SliME 2024.11	37.4	-	-	-	-	-	-

Showing 100 of 282 rows