List your company

Scientific QA on SCIMDR Eval

49.9AccuracyGPT-5.2
3.82815.78927.7539.711Mar 12, 2026

Evaluation results

MethodLinks
GPT-5.2Model=GPT-5.22026.0349.9
Qwen2.5-VL-7B + SCIMDRModel=Qwen2.5-VL-7B, Training Data=SCIMDR2026.0349.1
GPT-5.1Model=GPT-5.12026.0347.2
Qwen-3-VL-8BModel=Qwen-3-VL-8B2026.0334.2
Qwen2.5-VL-7BModel=Qwen2.5-VL-7B, Training Data=None2026.0319.8
InternVL-3-8BModel=InternVL-3-8B2026.0316.8
LLaVA-OV-1.5-8BModel=LLaVA-OV-1.5-8B2026.0315.5
Qwen2.5-VL-7B + SPIQAModel=Qwen2.5-VL-7B, Training Data=SPIQA2026.035.6