MMVetGPT4Turbo

multimodal
+
+
+
+
About

MMVet-GPT4Turbo is a specialized variant of the MM-Vet benchmark specifically optimized for evaluation using GPT-4 Turbo as the assessment model. This version leverages GPT-4 Turbo's enhanced capabilities to provide more accurate and reliable evaluation of large multimodal models across the same six core vision-language capabilities and their integrations.

+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers

Score Distribution

1 models
Top Score
74.0%
Average Score
74.0%
High Performers (80%+)
0

Top Organizations

#1Alibaba Cloud / Qwen Team
1 model
74.0%
+
+
+
+
Leaderboard
1 models ranked by performance on MMVetGPT4Turbo
LicenseLinks
Aug 29, 2024
tongyi-qianwen
74.0%
+
+
+
+
Resources