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...

BTZSC - Emotion — leaderboard

Metric: Macro-F1 (%). Source: huggingface.co. 35 models tracked.

Top models

#ModelScore
1Qwen 3 4B37.28
2Mistral Nemo Instruct (2407)36.28
3Llama 3.2 3B Instruct34.79
4Qwen 3 8B32.41
5Phi-4 Mini Instruct30.02
6Gemma 3 1B (IT)14.37

Interactive version: theaggregate.ai/benchmark?slug=btzsc-emotion · 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.