The Model Index
Up to four models

Llama 3 vs Llama 2

On the index (GPT-4 = 100), Llama 3 scores 101 and Llama 2 95. 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 Llama 3
Presets
Llama 3
10184–118
WeightsOpen
ReleasedApr 2024
Price in / out–
Context–
Core tests taken1 of 9
Llama 2
9579–111
WeightsOpen
ReleasedJul 2023
Price in / out–
Context–
Core tests taken1 of 9

Llama 3 and Llama 2 are too close to call (6 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Llama 3Llama 2
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
TestLlama 3Llama 2
Reasoning & knowledge
GPQA Diamond (Epoch AI)40.6%26.3%
MMLU (HELM runs)79.3%69.5%
Maths
AIME-style maths (OTIS mock)4.3%0.0%
MATH (level 5)22.6%3.3%
Agents
DTBench54.2%41.6%

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

This page as a chartDownload PNG