Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Llama 3.1 8B vs Mistral Small 3 24B Base

Meta 🇺🇸

4.0

#362—

Mistral Small 3 24B Base

Mistral AI 🇫🇷

4.5

#359—

Category Comparison

Benchmark-by-Benchmark

coding

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
HumanEval	72.6	—

language

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
WinoGrande	78.9	—
HellaSwag	82	—

general

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
MMLU-Pro	48.3	—
Chatbot Arena Elo	1141	—
IFEval	73.1	—

math

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
MATH	51.9	—
GSM8K	84.5	—

reasoning

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
ARC-Challenge	83.4	—
GPQA Diamond	—	34.4

safety

Benchmark	Llama 3.1 8B	Mistral Small 3 24B Base
TruthfulQA	52.4	—

Category Winners

coding

Llama 3.1 8B

8.1

math

Llama 3.1 8B

5.1

reasoning

Mistral Small 3 24B Base

4.5

general

Llama 3.1 8B

4.4

language

Llama 3.1 8B

1.8

safety

Llama 3.1 8B

3.2

Llama 3.1 8B vs Mistral Small 3 24B Base — Benchmark Comparison | Neura Market