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

Spatial Reasoning on CV-Bench

92Accuracy

GEMINI-3-PRO-PREVIEW

Updated 4d ago

Evaluation Results

Method	Links
GEMINI-3-PRO-PREVIEW 2026.02		92
RoboBrain2.0-7B 2025.12		86.44
GEMINI-2.5-PRO 2026.02		85.9
RoboBrain-7B-2.0 2026.01		85.75
Qwen3-VL-8B 2025.12		85.69
VST-7B-SFT 2026.02		85.5
GPT-o4-mini-2025-05-16 2026.01		85.21
GPT-4o-mini 2025.12		85.21
SEED-1.6 2026.02		85.2
QWEN3-VL-8B-INSTRUCT 2026.02		85.1
GeoThinker QWEN3VL-8B 2026.02		85.1
GPT-5 2026.02		84.6
Gemini-2.5-Pro-preview-05-06 2026.01		84.59
Gemini-2.5-pro 2025.12		84.59
VST-3B-SFT 2026.02		84.4
Gemini-2.5-Flash-preview-04-17 2026.01		84.03
RoboBrain-32B-2.0 2026.01		83.92
GenieReasoner 2025.12		83.89
Action-Sketcher-3B 2026.01		82.89
VG-LLM-8B 2026.02		82.7
Qwen2.5-VL-72B-Instruct 2026.01		82.68
InternVL-3.5-8B 2025.12		82.16
GeoThinker QWEN2.5VL-7B 2026.02		82.1
VG-LLM-8B* 2026.02		81.7
Qwen2.5-VL-32B-Instruct 2026.01		81.59
INTERNVL3-8B 2026.02		81
VG-LLM-4B 2026.02		81
Qwen2.5-VL-7B 2025.12		80.78
GPT-4o-2024-11-20 2026.01		78.63
VeBrain-8B 2026.01		78.57
Claude-Sonnet-4-2025-05-14 2026.01		78.43
QWEN3-VL-2B-INSTRUCT 2026.02		78.4
CAMBRIAN-S-7B 2026.02		76.9
INTERNVL3-2B 2026.02		76.5
RoboBrain-7B-1.0 2026.01		76.22
BAGEL-7B-MOT 2026.02		76
Claude-Sonnet-4 2025.12		75.8
QWEN2.5-VL-7B-INSTRUCT 2026.02		75.4
CAMBRIAN-S-3B 2026.02		75.2
Cosmos-Reason1-7B 2025.12		75.2
Cosmos-Reason1-7B 2026.01		74.71
SPATIALLADDER-3B 2026.02		73.7
QWEN2.5-VL-3B-INSTRUCT 2026.02		71.8
VLM-3R-7B 2026.02		71.8
Qwen2.5-VL-3B 2025.12		71.29
Magma-8B 2026.01		60.98