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

Multimodal Reasoning on SPD-Faith Bench Easy 1.0

5Contradiction Rate

GPT-4o

Updated 3d ago

Evaluation Results

Method	Links
GPT-4o 2026.02		5
GLM-4.5V 2026.02		8
Qwen3-VL-235B-A22B 2026.02		10.5
Qwen3-VL-32B 2026.02		16
Gemini-2.5-Pro 2026.02		16.5
Claude-4.5-Haiku 2026.02		16.5
Qwen2.5-VL-72B 2026.02		19
InternVL2.5-38B 2026.02		19.2
Qwen2.5-VL-7B 2026.02		23
MiniCPM-V-2.6 2026.02		23
InternVL2.5-8B 2026.02		32.5
DeepSeek-VL2 2026.02		39.5