Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
LLM Benchmark Hub
Loading data...

Seeing Culture - Grounding mIoU — leaderboard

Metric: Overall mIoU (%). Source: seeingculture-benchmark.github.io. 6 models tracked.

Top models

#ModelScore
1O331.78
2Gemini 2.5 Pro16.22
3GPT-4.113.74

Interactive version: aibenchmarks.dev/benchmark?slug=seeing-culture-grounding-miou · How the rankings work · Data refreshed daily, snapshot 2026-07-20.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.