Skip to content
The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps Task Explorer Builder
How It Works About Guesswork Metrics
The Aggregate
Loading data...

HELM SeaHELM - XCOPA (th): leaderboard

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

Top models

#ModelScore
1Claude 3.7 Sonnet (20250219)97.8
2Qwen 2.5 72B Instruct97.4
3GPT-4o (2024-11-20)97.2
4Llama 3.1 70B Instruct96.2
5Llama 3.3 70B Instruct96
6Llama 3.2 90B Vision Instruct96
7Llama 3.1 405B Instruct95.8
8Gemini 2.0 Flash95.6
9DeepSeek V395.4
10Gemini 2.0 Flash Lite95.2
11Qwen 2 72B Instruct94.4
12GPT-4o Mini (2024-07-18)93.6
13Llama 4 Maverick Instruct FP886.4
14Claude 3.5 Haiku (20241022)86.2
15Llama 4 Scout Instruct56.6

Interactive version: theaggregate.ai/benchmark?slug=helm-seahelm-xcopa-th · How It Works · Data refreshed daily, snapshot 2026-09-05.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.
A

Your Aggregate

Sign in to keep your work

Save custom rankings and get 50 free task analyses each day.

Continue with Google Continue with GitHub

No password to remember. Your public profile identifies saved work.

Your Aggregate

Account

  • Saved custom aggregate views
  • 50 free task analyses per day
Sign out