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...

VinCLAT (Catalan) — leaderboard

Metric: Average Accuracy (%). Source: huggingface.co. 18 models tracked.

Top models

#ModelScore
1DeepSeek R128.25
2Qwen 3 235B A22B17.48
3DeepSeek V3 (0324)9.6
4Qwen 3 32B6.1
5Qwen 3 14B3.03
6Qwen 3 30B A3B2.38
7Qwen 3 8B1.63
8Qwen 3 4B0.75
9Qwen 3 1.7B0.15
10Qwen 3 0.6B0.05

Interactive version: theaggregate.ai/benchmark?slug=vinclat-catalan · 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.