The Model Index
Up to four models

GPT-4o (Aug 2024) vs Llama 3.1

On the index (GPT-4 = 100), GPT-4o (Aug 2024) scores 112 and Llama 3.1 110. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-4o (Aug 2024)
Presets
GPT-4o (Aug 2024)
11295–128
WeightsClosed
ReleasedAug 2024
Price in / out$2.5 / $10
Context128K
Core tests taken2 of 9
Llama 3.1
11094–127
WeightsOpen
ReleasedJul 2024
Price in / out–
Context–
Core tests taken1 of 9

GPT-4o (Aug 2024) and Llama 3.1 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

GPT-4o (Aug 2024)Llama 3.1
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)SimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)
Every result as a table
TestGPT-4o (Aug 2024)Llama 3.1
Reasoning & knowledge
GPQA Diamond (Epoch AI)49.2%50.9%
MMLU (HELM runs)84.3%84.5%
SimpleBench17.8%23.0%
Maths
AIME-style maths (OTIS mock)6.4%9.7%
MATH (level 5)53.3%49.8%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG