Share your thoughts, 1 month free Claude Pro on usSee more

Visual Question Answering on VQA 2.0 (val)

86.1Accuracy (Overall)

Molmo2-8B

Updated 1d ago

Evaluation Results

Method
Molmo2-8B 2026.05	86.1	-	-	-	-
Molmo2-4B 2026.05	85.3	-	-	-	-
Molmo2-4B 2026.05	85.3	-	-	-	-
PerceptionLM-8B 2026.05	84	-	-	-	-
DeepSeek-VL2-16B-A2.4B 2026.05	83.7	-	-	-	-
MolmoE-8B-A1B 2026.05	82.8	-	-	-	-
Zamba2-VL-7B 2026.05	82.8	-	-	-	-
Zamba2-VL-7B 2026.05	82.8	-	-	-	-
Qwen3-VL-8B 2026.05	82.5	-	-	-	-
Qwen3-VL-4B 2026.05	80.7	-	-	-	-
Qwen3-VL-4B 2026.05	80.7	-	-	-	-
Qwen3.5-4B 2026.05	80.4	-	-	-	-
ZAYA1-VL-8B-A1B 2026.05	80	-	-	-	-
PerceptionLM-1B 2026.05	80	-	-	-	-
Qwen2.5-VL-3B 2026.05	79.6	-	-	-	-
Zamba2-VL-2.7B 2026.05	79.6	-	-	-	-
Zamba2-VL-2.7B 2026.05	79.6	-	-	-	-
Cobra-8B 2026.05	79.2	-	-	-	-
Qwen3-VL-2B 2026.05	78.8	-	-	-	-
Qwen3-VL-2B 2026.05	78.8	-	-	-	-
InternVL3.5-8B 2026.05	78.6	-	-	-	-
InternVL3.5-20B-A4B 2026.05	78.4	-	-	-	-
Qwen3.5-2B 2026.05	78.3	-	-	-	-
Zamba2-VL-1.2B 2026.05	78	-	-	-	-
Zamba2-VL-1.2B 2026.05	78	-	-	-	-
Cobra-3.5B 2026.05	77.8	-	-	-	-
PLM-3B 2026.05	77.3	-	-	-	-
PerceptionLM-3B 2026.05	76.9	-	-	-	-
VL-Mamba2.8B 2026.05	76.6	-	-	-	-
SimVLMhuge 2021.08	76.5	-	-	-	-
InternVL3.5-4B 2026.05	76.4	-	-	-	-
InternVL3.5-4B 2026.05	76.4	-	-	-	-
Mamba-VL-2.8B 2026.05	76.1	-	-	-	-
SimVLMlarge 2021.08	76	-	-	-	-
SimVLMhuge 2021.08	75.5	-	-	-	-
SimVLMlarge 2021.08	75.2	-	-	-	-
Pythia-VL-2.8B 2026.05	75.1	-	-	-	-
Mamba-VL-1.4B 2026.05	74.5	-	-	-	-
SimVLMbase 2021.08	73.8	-	-	-	-
Oscar 2021.09	73.8	-	-	-	-
InternVL3.5-2B 2026.05	73.6	-	-	-	-
Pythia-VL-1.4B 2026.05	73.6	-	-	-	-
InternVL3.5-2B 2026.05	73.6	-	-	-	-
SimVLMbase 2021.08	73.2	-	-	-	-
Pythia-VL-1B 2026.05	72.3	-	-	-	-
Mamba-VL-0.8B 2026.05	71.7	-	-	-	-
CFR 2021.10	69.7	-	-	-	-
InternVL3.5-1B 2026.05	69.6	-	-	-	-
MCANed-6 2019.06	67.23	-	-	-	0.01
MCAN 2021.10	67.2	-	-	-	-
REGAT 2021.10	67.2	-	-	-	-
Pythia 2021.10	66.3	-	-	-	-
DFAF 2021.10	66.2	-	-	-	-
BAN-8 2019.06	66.04	-	-	-	0.08
BAN2-CTI 2019.09	66	-	-	-	-
BAN 2021.10	66	-	-	-	-
CTI 2021.10	66	-	-	-	-
MFH 2019.06	65.65	-	-	-	0.05
BAN2 2019.09	65.6	-	-	-	-
HAN 2021.10	65.5	-	-	-	-
MuRel 2021.10	65.1	-	-	-	-
XNMs 2018.12	64.7	-	-	-	-
UpDn 2019.05	63.5	81.2	42.1	55.7	-
Up-Down 2018.12	63.2	-	-	-	-
Bottom-up 2019.09	63.2	-	-	-	-
Baseline architecture 2019.06	63.1	-	-	-	-
UpDn+AdvReg. 2019.05	62.8	79.8	42.4	55.2	-
UpDn+HINT 2019.05	62.5	80.5	41.8	54	-
UpDn+SCR 2019.05	62.3	77.4	40.9	56.5	-
UpDn+SCR 2019.05	62.2	78.9	41.4	54.3	-
UpDn+SCR 2019.05	62.2	78.8	41.6	54.5	-
SAN-CTI 2019.09	62.1	-	-	-	-
SAN 2019.09	61.7	-	-	-	-
fPMC 2021.10	61.7	-	-	-	-
RUBi 2019.06	61.16	-	-	-	-
VQ2A 2022.12	61.1	-	-	-	-
UpDn+AttAlign 2019.05	61	78.9	38.4	53.3	-
Img2LLM 175B 2022.12	60.6	-	-	-	-
Img2LLM 66B 2022.12	59.9	-	-	-	-
PICa-Full 2021.09	59.7	-	-	-	-
Show, Ask, Attend, and Answer 2017.04	59.67	77.45	38.46	51.76	-
Img2LLM 30B 2022.12	59.5	-	-	-	-
MCB 2017.04	59.14	77.37	36.66	51.23	-
Img2LLM 6.7B 2022.12	57.6	-	-	-	-
Img2LLM 13B 2022.12	57.1	-	-	-	-
Flamingo 80B 2022.12	56.3	-	-	-	-
PICa-Full 2021.09	56.1	-	-	-	-
PICa175B-Ensemble 2022.12	56.1	-	-	-	-
PICa-Full 2023.03	56.1	-	-	-	-
PICa-Full 2021.09	55.9	-	-	-	-
HieCoAtt 2017.04	54.57	71.8	36.53	46.25	-
PICa-Base 2021.09	54.3	-	-	-	-
PICa175B+ 2022.12	54.3	-	-	-	-
PICa-Base 2023.03	54.3	-	-	-	-
PICa-Base 2021.09	53.2	-	-	-	-
FewVLM large 2022.12	51.1	-	-	-	-
TAP-C 2022.03	50.18	73.51	31.56	37.35	-
MixPHM 2023.03	49.3	-	-	-	-
TAP-C 2022.03	49.19	73.6	32.55	35.02	-
TAP-C 2022.03	48.89	72.98	29.96	35.58	-

Showing 100 of 183 rows