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...

HSCodeComp - 4-digit — leaderboard

Metric: Exact Match Accuracy (%). Source: arxiv.org. 14 models tracked.

Top models

#ModelScore
1Gemini 2.5 Pro69.94
2GPT-569.78
3Claude Sonnet 462.97
4Kimi K262.03
5DeepSeek R161.71
6GPT-4o61.55
7O3 Mini56.17
8DeepSeek V354.43
9Qwen 3 235B A22B49.53
10Qwen Max48.58
11Qwen 3 32B29.27
12QwQ-32B29.11
13Qwen 2.5 72B12.34

Interactive version: theaggregate.ai/benchmark?slug=hscodecomp-4-digit · 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.