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 - LLM — leaderboard

Metric: Macro-F1 (%). Source: huggingface.co. 7 models tracked.

Top models

#ModelScore
1Mistral Nemo Instruct (2407)66.97
2Qwen 3 8B66.49
3Qwen 3 4B64.86
4Phi-4 Mini Instruct43.09
5Llama 3.2 3B Instruct43.02
6Gemma 3 1B (IT)35.91

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