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 (id) — leaderboard

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

Top models

#ModelScore
1Qwen 2.5 72B Instruct98
2Claude 3.7 Sonnet (20250219)98
3Gemini 2.0 Flash97.4
4Llama 3.2 90B Vision Instruct96.8
5Qwen 2 72B Instruct96.8
6GPT-4o (2024-11-20)96.8
7Llama 3.1 70B Instruct96.2
8Gemini 2.0 Flash Lite94.8
9GPT-4o Mini (2024-07-18)94.6
10Llama 3.3 70B Instruct91
11DeepSeek V385
12Claude 3.5 Haiku (20241022)75.8
13Gemma 2 9B (IT)61.6
14DeepSeek R1 Distill Llama 8B58.8
15Llama 4 Scout Instruct47

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