The Model Index
Up to four models

Llama 2 vs GPT-3.5 Turbo (Jan 2024)

On the index (GPT-4 = 100), Llama 2 scores 95 and GPT-3.5 Turbo (Jan 2024) 90. 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 2
Presets
Llama 2
9579–111
WeightsOpen
ReleasedJul 2023
Price in / out–
Context–
Core tests taken1 of 9
GPT-3.5 Turbo (Jan 2024)
9072–109
WeightsClosed
ReleasedJan 2024
Price in / out–
Context–
Core tests taken2 of 9

Llama 2 and GPT-3.5 Turbo (Jan 2024) are too close to call (5 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

Llama 2GPT-3.5 Turbo (Jan 2024)
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 2GPT-3.5 Turbo (Jan 2024)
Reasoning & knowledge
GPQA Diamond (Epoch AI)26.3%27.2%
MMLU (HELM runs)69.5%67.3%
Maths
AIME-style maths (OTIS mock)0.0%2.2%
MATH (level 5)3.3%11.6%
Agents
DTBench41.6%48.5%

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

This page as a chartDownload PNG