The Model Index
Up to four models

Mistral Large 2 vs Llama 3.3 70B

On the index (GPT-4 = 100), Mistral Large 2 scores 109 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 Large 2
Presets
Mistral Large 2
10992–125
WeightsOpen
ReleasedJul 2024
Price in / out–
Context–
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 Large 2 and Llama 3.3 70B are too close to call (1 point apart, within the uncertainty), ahead on 1 of 1 shared core tests.

Test by testthird-party results

Mistral Large 2Llama 3.3 70B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MMLU (HELM runs)MMLU (HELM runs)SimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)AGENTSDTBenchDTBench
Every result as a table
TestMistral Large 2Llama 3.3 70B
Reasoning & knowledge
GPQA Diamond (Epoch AI)49.0%47.4%
MMLU (HELM runs)80.0%79.1%
SimpleBench22.5%19.9%
Maths
AIME-style maths (OTIS mock)8.5%5.1%
MATH (level 5)44.8%41.6%
Agents
DTBench61.2%59.5%

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

This page as a chartDownload PNG