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

Multimodal Reasoning on MMBench CN

81.8Accuracy

Vanilla

Updated 4d ago

Evaluation Results

Method	Links
Vanilla 2026.02		81.8
InternVL2-8B-FT 2024.08		81.5
InternVL2-8B + RP 2024.08		81.4
PIO-FVLM 2026.02		80.5
DART 2026.02		79
PIO-FVLM 2026.02		78.1
DART 2026.02		76.5
PIO-FVLM 2026.02		75.5
DART 2026.02		71.5
LLaVA-1.5-13B + MMFuser 2024.10		63.8
LLaVA-1.5-13B 2024.10		63.6
LLaVA-1.5-7B + MMFuser 2024.10		60.1
LLaVA-1.5-7B + RP 2024.08		59.8
MGM-7B + RP 2024.08		59.6
MGM-7B 2024.08		58.9
LLaVA-1.5-7B 2024.10		58.3
LLaVA-1.5-7B 2024.08		58.3
Qwen-VL-Chat 2024.10		56.7
IDEFICS-80B 2024.10		38.1
IDEFICS-9B 2024.10		25.2
InstructBLIP 2024.10		23.7
Qwen-VL 2024.10		7.4