The Model Index
Up to four models

GPT-3.5 Turbo (Jan 2024) vs Llama 3.1-8B

On the index (GPT-4 = 100), GPT-3.5 Turbo (Jan 2024) scores 90 and Llama 3.1-8B 89. 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-3.5 Turbo (Jan 2024)
Presets
GPT-3.5 Turbo (Jan 2024)
9072–109
WeightsClosed
ReleasedJan 2024
Price in / out–
Context–
Core tests taken2 of 9
Llama 3.1-8B
8970–107
WeightsOpen
ReleasedJul 2024
Price in / out$0.020 / $0.040
Context131K
Core tests taken1 of 9

GPT-3.5 Turbo (Jan 2024) and Llama 3.1-8B are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

GPT-3.5 Turbo (Jan 2024)Llama 3.1-8B
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)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGPT-3.5 Turbo (Jan 2024)Llama 3.1-8B
Reasoning & knowledge
GPQA Diamond (Epoch AI)27.2%27.0%
MMLU (HELM runs)67.3%56.1%
Maths
AIME-style maths (OTIS mock)2.2%1.7%
MATH (level 5)11.6%22.9%
Coding
WeirdML3.5%1.7%
Agents
DTBench48.5%50.9%
LMCA9.7%5.4%

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

This page as a chartDownload PNG