The Model Index
Up to four models

Llama 3.1-8B vs Mistral 7B v0.3

On the index (GPT-4 = 100), Llama 3.1-8B scores 89 and Mistral 7B v0.3 82. 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 3.1-8B
Presets
Llama 3.1-8B
8970–107
WeightsOpen
ReleasedJul 2024
Price in / out$0.020 / $0.040
Context131K
Core tests taken1 of 9
Mistral 7B v0.3
8261–102
WeightsOpen
ReleasedMay 2024
Price in / out–
Context–
Core tests taken1 of 9

Llama 3.1-8B and Mistral 7B v0.3 are too close to call (7 points apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Llama 3.1-8BMistral 7B v0.3
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 3.1-8BMistral 7B v0.3
Reasoning & knowledge
GPQA Diamond (Epoch AI)27.0%15.2%
MMLU (HELM runs)56.1%59.9%
Maths
AIME-style maths (OTIS mock)1.7%0.3%
MATH (level 5)22.9%3.7%
Agents
DTBench50.9%42.5%

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

This page as a chartDownload PNG