The Model Index
Up to four models

GPT-4o vs Llama 3.1

On the index (GPT-4 = 100), GPT-4o scores 111 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
Presets
GPT-4o
11195–127
WeightsClosed
ReleasedMay 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 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-4oLlama 3.1
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)AGENTSDTBenchDTBench
Every result as a table
TestGPT-4oLlama 3.1
Reasoning & knowledge
GPQA Diamond (Epoch AI)48.9%50.9%
MMLU (HELM runs)84.2%84.5%
Maths
AIME-style maths (OTIS mock)6.3%9.7%
MATH (level 5)51.0%49.8%
Agents
DTBench64.5%61.4%
Task length · METR24 sec

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

This page as a chartDownload PNG