Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

Meta Llama

🇺🇸 16 models · USA · 56 Benchmarks

Leaderboard position

#118
Company rank (of 237 companies)
#433
Best model overall
191
Average Elo
16
Models
56
Benchmarks covered
Above: cactus-compute #424 Below: Sapbot #436

Model highlights

Best model
Meta Llama: Llama 4 Maverick Instruct
#433 1237 Elo · 14 benchmarks
Lowest-ranked model
Meta Llama: llama-3.2-1b-instruct
#1103 -767 Elo · 4 benchmarks

Nearest competitor company

The company with the most similar benchmark results.

appeared as nearest in 7 of 56 benchmarks

DeepSeek
7/56 12.5%
Company Votes % of benchmarks
DeepSeek 7 12.5%
Qwen 6 10.7%
OpenBMB 4 7.1%
Xiaomi 3 5.4%
Yandex 3 5.4%
Anthropic 3 5.4%
Google 3 5.4%
SpaceXAI 2 3.6%
OpenAI 2 3.6%
JetBrains 2 3.6%

Models

Rank Model
🇺🇸 433 Meta Llama: Llama 4 Maverick Instruct compare
🇺🇸 609 Meta Llama: Llama 4 Scout Instruct compare
🇺🇸 612 Meta Llama: Llama 3.1 405B Instruct compare
🇺🇸 722 Meta Llama: Llama 3.3 70B Instruct compare
🇺🇸 779 Meta Llama: llama-3.1-70b-instruct compare
🇺🇸 830 Meta Llama: Llama 3.2 3B compare
🇺🇸 861 Meta Llama: Llama 3.2 90B Instruct compare
🇺🇸 908 Meta Llama: Llama 3.2 3B Instruct compare
🇺🇸 955 Meta Llama: Llama 3 70B Instruct compare
🇺🇸 961 Meta Llama: Llama 3.1 8B Instruct compare
🇺🇸 966 Meta Llama: llama-2-7b-chat compare
🇺🇸 1004 Meta Llama: llama-3.2-11b-instruct compare
🇺🇸 1027 Meta Llama: llama-2-13b-chat compare
🇺🇸 1031 Meta Llama: llama-2-70b-chat compare
🇺🇸 1098 Meta Llama: meta-llama-3-8b-instruct compare
🇺🇸 1103 Meta Llama: llama-3.2-1b-instruct compare