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

Visual Question Answering on AI2D

87.3Accuracy

Baseline

Updated 2d ago

Evaluation Results

Method	Links
Baseline 2026.01		87.3
PTQ 2026.01		86.8
QAD 2026.01		86.7
QAT 2026.01		86.5
EMOVA 2024.09		85.8
InternVL3 2025.10		85.2
GPT-4o 2024.09		84.6
InternVL2.5 2025.10		84.5
Qwen2.5-VL 2025.10		83.9
PTP 2025.09		83.8
NEO 2025.10		83.1
MoVA 2024.04		83
Qwen2-VL 2025.10		83
Encoder-Based 2025.10		82.9
InternVL2-8B 2025.09		82.4
RADIOv2.5-H + Tiling 2024.12		82.4
GSearch 2025.09		82.1
VTW 2025.09		81.8
EMOVA 2024.09		81.7
Qwen2.5-VL 3B (reported) 2025.12		81.6
Qwen2.5-VL 2025.10		81.6
Qwen3-VL-4B-Instruct 2026.02		81.6
GeminiProVision 2024.06		81.4
PALI-X-55B 2023.08		81.2
PALI-X-55B 2024.04		81.2
MG-LLAVA 2024.06		81.1
FastV 2025.09		81.1
PDrop 2025.09		80.4
Gemini Pro 1.5 2024.09		80.3
Qwen2.5-VL 3B (reproduced) 2025.12		80.1
NEO 2025.10		80.1
VITA 2024.09		79.3
SigLIP SO400M + Tiling 2024.12		79.3
LaViDa-R1 2026.02		78.9
InternVL3 2025.10		78.7
Xiaomi-Robotics-0 2026.02		78.7
EMOVA 2024.09		78.6
LaViDa-O +SFT 2026.02		78.6
GPT-4V 2024.09		78.2
LLaDA-V 2026.01		77.82
LLaDA-FastV 2026.01		77.75
Encoder-Based 2025.10		77.4
MoVA 2024.04		77
LaViDa-O 2026.02		76.7
SAIL 2025.10		76.7
BREEN 2025.10		76.4
LLaDA-FastV 2026.01		75.87
MG-LLAVA 2024.06		75.6
INF-LLaVA* 2024.07		75.42
CROME-Vicuna-7B 2024.08		75.3
MG-LLAVA 2024.06		75.1
CASA⊕ Qwen2.5-VL 2025.12		75.1
MoVA 2024.04		74.9
InternVL2.5 2025.10		74.9
EVEv2 2025.10		74.8
Qwen2-VL 2025.10		74.7
Dimple 2026.02		74.4
DAVE 2025.12		74
SigLIP 2 2025.12		73.6
MG-LLAVA 2024.06		73.4
VITA 2024.09		73.1
HoVLE 2025.10		73
Fused 2026.02		72.83
PTP 2025.09		72.6
InternVL2-2B 2025.09		72.5
Avg 2026.02		72.41
OneCAT 2025.10		72.4
MaD-Mix 2026.02		72.15
MolmoAct 2026.02		72
GSearch 2025.09		71.9
RADIOv2.5-H 2024.12		71.9
Uniform 2026.02		71.83
FastV 2025.09		71.6
Raw-FastV 2026.01		71.5
Spatially-R 2025.09		70.8
PDrop 2025.09		70.6
LLaVA-NeXT 2024.06		70
LaViDa-L 2026.02		70
Emu3 2025.10		70
AIMv2 2025.12		69.7
Random 2025.09		69.7
TTAdapt 2025.10		69.7
TTAug 2025.10		69.6
MG-LLAVA 2024.06		69.3
BLIVA-Vicuna-7B 2024.08		69.2
In-Squeeze (128 ... -> 1) 2026.02		68.71
Mono-InternVL 2025.10		68.6
Baseline 2025.10		68.5
Cont-Squeeze (128 -> 1) 2026.02		68.3
Dragonfly 2024.06		67.9
Direct Fine-tuning (r=1) 2026.02		67.73
Cont-Squeeze (128 -> 1) 2026.02		67.73
In-Squeeze (128 ... -> 1) 2026.02		67.73
Mono-InternVL-1.5 2025.10		67.4
TTAdapt 2025.10		67.4
Cont-Squeeze (128 -> 1) 2026.02		67.37
AVG-LLaVA 2024.09		67.3
Direct Fine-tuning (r=1) 2026.02		67.16
Raw-FastV 2026.01		66.87
VTW 2025.09		66.8

Showing 100 of 174 rows