Neura Intelligence Index

AI Model Benchmarks

Llama 3.1 405B vs Mistral Medium 3.5 — Benchmark Comparison | Neura Market

Back to Leaderboard

Llama 3.1 405B vs Mistral Medium 3.5

Meta 🇺🇸

66.3

#89—

Mistral Medium 3.5

Mistral AI 🇫🇷

64.9

#92—

Category Comparison

Benchmark-by-Benchmark

coding

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
HumanEval	89	—
SWE-bench Verified	—	77.6

math

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
MATH	73.8	—
GSM8K	96.8	—
AIME 2025	—	86.3

language

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
WinoGrande	87.6	—
HellaSwag	96	—

reasoning

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
BigBench-Hard	85.4	—
GPQA Diamond	51.1	—
ARC-Challenge	96.9	—

general

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
IFEval	86.4	—
Chatbot Arena Elo	1244	—
MMLU-Pro	73.3	—

safety

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
TruthfulQA	65.3	—

agent

Benchmark	Llama 3.1 405B	Mistral Medium 3.5
BrowseComp	—	48.6

Category Winners

coding

Mistral Medium 3.5

77.0

math

Llama 3.1 405B

72.0

reasoning

Llama 3.1 405B

48.9

general

Llama 3.1 405B

67.9

language

Llama 3.1 405B

87.7

safety

Llama 3.1 405B

59.8

agent

Mistral Medium 3.5

21.5