BenchLMM — leaderboard

Metric: GPT-3.5 score. Source: huggingface.co. 10 models tracked.

Top models

#ModelScore
1GPT-4V58.37
2Sphinx-V2-1K57.43
3LLaVA-1.5-13B55.53
4LLaVA-1.5-7B46.83
5InstructBLIP-13B45.03
6InstructBLIP-7B44.63
7LLaVA-1-13B43.5
8Otter-7B39.13
9MiniGPT4-13B34.93
10MiniGPTv2-7B30.1

Interactive version: theaggregate.ai/benchmark?slug=benchlmm · How the rankings work · Data refreshed daily, snapshot 2026-07-22.