The Model Index
Up to four models

Mistral Small 3 vs Llama 3.3 70B

On the index (GPT-4 = 100), Mistral Small 3 scores 108 and Llama 3.3 70B 108. 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 Mistral Small 3
Presets
Mistral Small 3
10892–124
WeightsOpen
ReleasedJan 2025
Price in / out$0.050 / $0.080
Context33K
Core tests taken1 of 9
Llama 3.3 70B
10892–124
WeightsOpen
ReleasedDec 2024
Price in / out$0.71 / $0.71
Context131K
Core tests taken1 of 9

Mistral Small 3 and Llama 3.3 70B are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 12× less.

Test by testthird-party results

Mistral Small 3Llama 3.3 70B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)
Every result as a table
TestMistral Small 3Llama 3.3 70B
Reasoning & knowledge
GPQA Diamond (Epoch AI)47.3%47.4%
Maths
AIME-style maths (OTIS mock)6.7%5.1%
MATH (level 5)44.8%41.6%

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

This page as a chartDownload PNG