List your company

Multimodal Reasoning on SPD-Faith Bench Medium 1.0

11.3Contradiction RateQwen2.5-VL-7B
10.23217.44124.6531.859Feb 8, 2026

Evaluation results

MethodLinks
Qwen2.5-VL-7BModel Type=Open-Source, Parameters=7B2026.0211.3
Qwen3-VL-32BModel Type=Open-Source, Parameters=32B2026.0212.3
MiniCPM-V-2.6Model Type=Open-Source2026.0212.7
Qwen2.5-VL-72BModel Type=Open-Source, Parameters=72B2026.0213.2
GPT-4oModel Type=Proprietary2026.0214.6
Qwen3-VL-235B-A22BModel Type=Open-Source, Parameters=235B-A22B2026.0215.2
GLM-4.5VModel Type=Open-Source2026.0218.8
Gemini-2.5-ProModel Type=Proprietary2026.0221.9
InternVL2.5-38BModel Type=Open-Source, Parameters=38B2026.0222.4
InternVL2.5-8BModel Type=Open-Source, Parameters=8B2026.0229.7
Claude-4.5-HaikuModel Type=Proprietary2026.0230.1
DeepSeek-VL2Model Type=Open-Source2026.0238