Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

OpenCompass Multimodal - HallusionBench — leaderboard

Metric: Score (%). Source: rank.opencompass.org.cn. 104 models tracked.

Top models

#ModelScore
1SenseNova-V6-5-Pro66.7
2TeleMM-2.065.7
3Ovis2.5-9B65.3
4TeleMM-2.0-Thinking65.2
5GPT-5-2025080765.2
6MiniCPM-o-4_565
7Gemini-2.5-Pro64.1
8JT-VL-Chat-Mini64.1
9JT3.563.8
10MiMo-VL-7B63.8

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

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