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

Multimodal Reasoning on MMMU

83.89Accuracy

Gemini-2.5 (Pro)

Updated 3d ago

Evaluation Results

Method	Links
Gemini-2.5 (Pro) 2026.01		83.89
STEP3-VL-10B (PaCoRe) 2026.01		80.11
Seed-1.5-VL (Thinking) 2026.01		79.11
Qwen3-VL (Thinking) 2026.01		78.7
STEP3-VL-10B 2026.01		78.11
STEP3-VL-10B (SeRe) 2026.01		78.11
GLM-4.6V 2026.01		75.2
Qwen3-VL Thinking 2026.01		73.53
InternVL 3.5 2026.01		71.69
GLM-4.6V Flash 2026.01		71.17
MiMo-VL RL-2508 2026.01		71.14
Gemma-3-27B 2025.12		64.9
InternVL3-8B 2025.12		62.7
Gemini Ultra 2023.02		59.4
InternVL3.5-2B 2025.12		59
InternVL3.5 2025.12		59
ARM-Thinker-7B 2025.12		57.2
GPT-4V(ision) 2023.02		56.8
Qwen2.5-VL-7B 2025.12		55
Qwen3-VL-2B 2025.12		53.4
Qwen3-VL 2025.12		53.4
InternVL3.5-2B 2025.11		51.78
Qwen2.5-VL-3B 2025.11		51.67
InternVL3-2B 2025.12		48.6
InternVL3 2025.12		48.6
LLaVA + GMAIL 2026.02		48.3
SAIL-VL2 2025.12		47.7
AndesVL 2025.12		46.1
Qwen3-VL-2B 2025.11		45.78
jina-vlm 2025.12		45.6
LFM2-VL-3B 2025.11		45.33
LLaVA 2026.02		44.7
HyperVL ViTL 2025.12		44.6
HyperVL 2025.12		43.4
SAIL-VL1.5 2025.12		42.9
SmolVLM2-2.2B 2025.11		41.6
Ovis2 2025.12		41.4
Qwen2-VL-2B 2025.12		41.1
Qwen2-VL 2025.12		41.1
OpenFlamingo-2 2023.02		28.7
Multimodal-CoT 2023.02		28.7
Fuyu 2023.02		27.9
MiniGPT4-Vicuna 2023.02		26.8
Kosmos-2 2023.02		24.4