List your company

Scientific Information Verification on Sci-PRMBench Search Information Verification

74.58AccuracySci-PRM
28.87240.738552.60564.4715Jun 3, 2026

Evaluation results

MethodLinks
Sci-PRM2026.0674.587553.8562.6988.2
Qwen3-VL-8B2026.0662.0852.5843.2247.4474.44
GPT-5-Mini2026.0659.3247.7317.825.9387.01
Qwen3-VL-32B2026.065743.4227.7333.8576.24
Gemini-3-Flash2026.0656.6777.5338.5551.4983.47
Doubao-Search2026.0643.3337.4463.8747.229.83
GLM-4.6V2026.0642.1437.7872.0349.5622.65
Llama-3.2-11B-V2026.0630.6332.6468.4244.195.29