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 - IndoNLI — leaderboard

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

Top models

#ModelScore
1Qwen 2 72B Instruct86
2Claude 3.7 Sonnet (20250219)85.8
3Qwen 2.5 72B Instruct83.2
4GPT-4o (2024-11-20)83
5GPT-4o Mini (2024-07-18)81.3
6Gemini 2.0 Flash80
7Gemini 2.0 Flash Lite76.8
8Llama 3.1 405B Instruct70.9
9Llama 3.3 70B Instruct52.2
10Llama 3.1 70B Instruct37.1
11DeepSeek R1 Distill Llama 8B36.5
12Llama 4 Scout Instruct32.2
13Gemma 2 9B (IT)24.1
14Llama 3.2 90B Vision Instruct10.8
15Gemma 2 27B (IT)7.1

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