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...

TriViewBench — leaderboard

Metric: Overall (self-reported). Source: benchmarklist.com. 19 models tracked.

Top models

#ModelScore
1Gemini 2.5 Flash79.55
2Claude 3.7 Sonnet68.62
3Qwen 3 VL 32B Instruct61.38
4GPT-4o60.35
5Qwen 3 VL 8B Instruct60.32
6Qwen 3 VL 4B Instruct52
7Qwen 2.5 VL 32B Instruct44.59
8Qwen 2.5 VL 7B Instruct37.05
9InternVL3.5-8B36.34

Interactive version: theaggregate.ai/benchmark?slug=triviewbench · 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.