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 - 2-digit — leaderboard

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

Top models

#ModelScore
1GPT-582.59
2Gemini 2.5 Pro80.54
3Claude Sonnet 478.8
4Kimi K278.01
5DeepSeek R177.22
6O3 Mini77.22
7DeepSeek V377.06
8GPT-4o75.47
9Qwen Max71.52
10Qwen 3 235B A22B66.93
11QwQ-32B66.77
12Qwen 3 32B64.4
13Qwen 2.5 72B20.73

Interactive version: theaggregate.ai/benchmark?slug=hscodecomp-2-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.