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...

Honeyval — leaderboard

Metric: Interaction Length (self-reported). Source: benchmarklist.com. 6 models tracked.

Top models

#ModelScore
1GPT-5.4 Nano96.9
2Claude Haiku 4.591.6
3Gemini 2.5 Flash70.5
4Qwen 3.5 9B63.1
5Gemini 3 Flash (Preview)61.2

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