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

Multimodal Reasoning on MM-Vet

80.8MM-Vet Score

GPT-4o-0806

Updated 2d ago

Evaluation Results

Method
GPT-4o-0806 2025.01	80.8	-	-	-	-	-	-	-
GPT-4o-mini-0718 2025.01	74.6	-	-	-	-	-	-	-
Llama-3.2-90B-Vision-Inst 2025.01	74.1	-	-	-	-	-	-	-
PG-CoT 2025.12	73.5	-	-	-	-	-	-	-
Gemini-1.5-Pro 2025.01	71.3	-	-	-	-	-	-	-
Phantom 2024.09	70.8	-	-	-	-	-	-	-
Vanilla 2026.01	70.41	-	-	-	-	-	-	-
CAPA 2026.01	69.85	-	-	-	-	-	-	-
Claude3.5-Sonnet-0620 2025.01	68.7	-	-	-	-	-	-	-
MMRPT 2025.12	68.12	-	-	-	-	-	-	-
ThinkLite-VL 2025.12	67.8	-	-	-	-	-	-	-
Base 2025.12	67.4	-	-	-	-	-	-	-
BAGEL 2025.06	67.2	-	-	-	-	-	-	-
UniWorld-V1 2025.06	67.1	-	-	-	-	-	-	-
Qwen2.5-VL 2025.12	67.1	-	-	-	-	-	-	-
MIRROR 2026.02	66.7	-	-	-	-	-	-	-
MetaQuery-XL 2025.06	66.6	-	-	-	-	-	-	-
Adaptive-CoF 2026.02	66.21	-	-	-	-	-	-	-
LlamaV-o1 2025.01	65.4	-	-	-	-	-	-	-
CAPA 2026.01	64.25	-	-	-	-	-	-	-
GPT-4V 2024.09	63.6	-	-	-	-	-	-	-
Qwen2-VL 2024.09	62	-	-	-	-	-	-	-
Vanilla 2026.01	61.83	-	-	-	-	-	-	-
MMRPT 2025.12	60.62	-	-	-	-	-	-	-
Llava-CoT 2025.01	60.3	-	-	-	-	-	-	-
DeepEyes 2026.02	60.28	-	-	-	-	-	-	-
MiniCPM-V-2.6 2024.09	60	-	-	-	-	-	-	-
InternVL2 2024.09	60	-	-	-	-	-	-	-
Base 2025.12	59.4	-	-	-	-	-	-	-
Llama-3.2-11B-Vision-Inst 2025.01	57.6	-	-	-	-	-	-	-
LLaVA-OV 2025.06	57.5	-	-	-	-	-	-	-
LLaVA-OneVision 2024.09	57.5	-	-	-	-	-	-	-
LLaVA-NeXT 2025.06	57.4	-	-	-	-	-	-	-
Meteor 2024.05	57.3	-	-	-	-	-	-	-
Meteor 2024.05	57.3	-	-	-	-	-	-	-
InternVL2-8B 2025.01	56.9	-	-	-	-	-	-	-
MiniCPM-V2.6-8B 2025.01	56.3	-	-	-	-	-	-	-
VL-Rethinker 2026.02	56.19	-	-	-	-	-	-	-
TroL 2024.06	54.7	-	-	-	-	-	-	-
Phantom-3.8B 2024.09	54.4	-	-	-	-	-	-	-
Phantom-1.8B 2024.09	54.1	-	-	-	-	-	-	-
PixelReasoner 2026.02	52.98	-	-	-	-	-	-	-
CogVLM 2024.08	52.8	-	-	-	-	-	-	-
Cambrian-1 2024.09	51.7	-	-	-	-	-	-	-
TroL-3.8B 2024.09	51.1	-	-	-	-	-	-	-
TroL 2024.06	51.1	-	-	-	-	-	-	-
Ovis1.5-Gemma2-9B 2025.01	50.9	-	-	-	-	-	-	-
Silkie 2023.12	49.9	-	-	-	-	-	-	-
Canvas-of-thought 2026.02	49.8	36.1	75.2	18.5	24.9	73.1	-	78.5
Revisual-R1 2025.12	49.8	-	-	-	-	-	-	-
Qwen2-VL-2B 2024.12	49.5	-	-	-	-	-	-	-
Tree-of-thought 2026.02	47	33.3	67.7	17.7	22.9	65.3	-	73.1
Qwen-VL-Chat + DPO (GPT-4V as Best) 2023.12	45.9	-	-	-	-	-	-	-
Qwen-VL-Chat + SFT (ShareGPT4V) 2023.12	45.9	-	-	-	-	-	-	-
Qwen-VL-Chat 2023.12	45.7	-	-	-	-	-	-	-
Phantom-0.5B 2024.09	45.7	-	-	-	-	-	-	-
TroL-1.8B 2024.09	45.1	-	-	-	-	-	-	-
TroL 2024.06	45.1	-	-	-	-	-	-	-
InternVL2 2024.12	44.6	-	-	-	-	-	-	-
Qwen-VL-Chat + DPO (Longest as Best) 2023.12	44.5	-	-	-	-	-	-	-
VILA-1.5-40B 2025.01	44.4	-	-	-	-	-	-	-
HoVLE 2024.12	44.3	-	-	-	-	-	-	-
Canvas-of-thought 2026.02	44.2	34	62.2	22.4	26.1	59.2	-	60.4
Program-of-thought 2026.02	44	33.3	62.5	15.5	20	60	-	71.5
LLAVA-Next 2024.08	43.9	-	-	-	-	-	-	-
Mulberry-7B 2025.01	43.9	-	-	-	-	-	-	-
Iterative Reflection 2026.02	43.9	34	64.9	20.5	23.8	60.5	-	65.4
HoVLE 2024.12	43.8	-	-	-	-	-	-	-
Tree-of-thought 2026.02	43.8	32.7	59.3	20.2	25.7	57.3	-	57.7
MM1-3B 2024.09	43.7	-	-	-	-	-	-	-
MoAI 2024.05	43.7	-	-	-	-	-	-	-
MoAI 2024.05	43.7	-	-	-	-	-	-	-
MoAI 2024.06	43.7	-	-	-	-	-	-	-
MM1-3B-Chat 2024.12	43.7	-	-	-	-	-	-	-
Chain-of-thought 2026.02	42.8	31.5	65.3	18.7	22	63.6	-	71.5
Chain-of-thought 2026.02	42.7	35.3	57.3	19.6	24.2	58.1	-	60.8
Honeybee 2023.12	42.2	-	-	-	-	-	-	-
MM1-MoE-3B×64 2024.09	42.2	-	-	-	-	-	-	-
DeepSeek-VL 2024.05	41.5	-	-	-	-	-	-	-
DeepSeek-VL 2024.05	41.5	-	-	-	-	-	-	-
DeepSeek-VL 2024.06	41.5	-	-	-	-	-	-	-
ASMv2 2024.05	41.3	-	-	-	-	-	-	-
ASMv2 2024.05	41.3	-	-	-	-	-	-	-
ASMv2 2024.06	41.3	-	-	-	-	-	-	-
MiniCPM-V2-2.8B 2024.09	41	-	-	-	-	-	-	-
MiniCPM-V-2 2024.12	41	-	-	-	-	-	-	-
SPHINX-MoE 2024.08	40.9	-	-	-	-	-	-	-
Program-of-thought 2026.02	40.6	32	56.3	16.7	22	54.7	-	46.2
CoLLaVO 2024.05	40.3	-	-	-	-	-	-	-
CoLLaVO 2024.05	40.3	-	-	-	-	-	-	-
CoLLaVO 2024.06	40.3	-	-	-	-	-	-	-
SPHINX-2k 2023.11	40.2	-	-	-	-	-	-	-
Sphinx-2K 2024.03	40.2	-	-	-	-	-	-	-
mPLUG-Owl3 2024.08	40.1	-	-	-	-	-	-	-
Janus-Pro 2025.06	39.8	-	-	-	-	-	-	-
LLaVA-VT 2024.03	39.8	-	-	-	-	-	-	-
Iterative Reflection 2026.02	39.5	31.3	55.2	17.7	19.7	48.5	-	61.5
OmniFusion 2024.05	39.4	-	-	-	-	-	-	-
OmniFusion 2024.05	39.4	-	-	-	-	-	-	-
OmniFusion 2024.06	39.4	-	-	-	-	-	-	-

Showing 100 of 281 rows