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...

HELM SeaHELM - XCOPA (vi) — leaderboard

Metric: EM. Source: crfm.stanford.edu. 21 models tracked.

Top models

#ModelScore
1Claude 3.7 Sonnet (20250219)97.4
2Llama 3.3 70B Instruct96.4
3Qwen 2.5 72B Instruct96.2
4GPT-4o (2024-11-20)96
5Gemini 2.0 Flash95.8
6DeepSeek V395.4
7GPT-4o Mini (2024-07-18)95.4
8Llama 3.1 70B Instruct95
9Qwen 2 72B Instruct94.8
10Llama 3.1 405B Instruct94.8
11Gemini 2.0 Flash Lite94
12Claude 3.5 Haiku (20241022)87
13Llama 4 Scout Instruct68.8
14Gemma 2 27B (IT)68.2
15DeepSeek R1 Distill Llama 8B57.2

Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-xcopa-vi · 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.