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

Hallucination Evaluation on CRPE relation

79.1Accuracy

InternVL2.5-26B

Updated 2d ago

Evaluation Results

Method	Links
InternVL2.5-26B 2024.12		79.1
InternVL2.5-78B 2024.12		78.8
InternVL2.5-8B 2024.12		78.4
InternVL2.5-38B 2024.12		78.3
Qwen3-VL + DISCO (10K) 2026.02		77.92
Qwen3-VL + Textual (10K) 2026.02		77.85
Qwen3-VL 2026.02		77.68
InternVL2-40B 2024.12		77.6
InternVL2-Llama3-76B 2024.12		77.6
GPT-4o-20240513 2024.12		76.6
MiniCPM-v2.6 + HIPPO 2026.02		76.37
MiniCPM-v2.6 2026.02		76.32
InternVL2-8B 2024.12		75.8
InternVL2-26B 2024.12		75.6
InternVL2.5-4B 2024.12		75.5
InternVL-Chat-V1.5 2024.12		75.4
MiniCPM-V2.6 2024.12		75.2
Qwen2-VL-7B 2024.12		74.4
InternVL2-4B 2024.12		71.1
InternVL2.5-2B 2024.12		70.2
InternVL2-2B 2024.12		66.3
InternVL2.5-1B 2024.12		60.9
InternVL2-1B 2024.12		57.5