The Model Index
Up to four models

GPT-4 Turbo vs Llama 2

On the index (GPT-4 = 100), GPT-4 Turbo scores 107 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 GPT-4 Turbo
Presets
GPT-4 Turbo
10791–123
WeightsClosed
ReleasedNov 2023
Price in / out–
Context–
Core tests taken2 of 9
Llama 2
9579–111
WeightsOpen
ReleasedJul 2023
Price in / out–
Context–
Core tests taken1 of 9

GPT-4 Turbo leads Llama 2 by 12 points, ahead on 1 of 1 shared core tests.

Test by testthird-party results

GPT-4 TurboLlama 2
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)MATHSMATH (level 5)MATH (level 5)AGENTSDTBenchDTBench
Every result as a table
TestGPT-4 TurboLlama 2
Reasoning & knowledge
GPQA Diamond (Epoch AI)42.4%26.3%
MMLU (HELM runs)79.6%69.5%
Maths
MATH (level 5)40.0%3.3%
Agents
DTBench61.6%41.6%
Task length · METR21 sec

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

This page as a chartDownload PNG