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 (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 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.