Neura Intelligence Index

AI Model Benchmarks

Gemini 1.0 Pro vs Llama 3.1 8B — Benchmark Comparison | Neura Market

Back to Leaderboard

Gemini 1.0 Pro vs Llama 3.1 8B

Google 🇺🇸

4.2

#340—

Meta 🇺🇸

4.0

#343—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
GPQA Diamond	27.9	—
ARC-Challenge	—	83.4

multimodal

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
MMMU	47.9	—

general

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
Chatbot Arena Elo	—	1141
MMLU-Pro	—	48.3
IFEval	—	73.1

coding

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
HumanEval	—	72.6

language

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
WinoGrande	—	78.9
HellaSwag	—	82

math

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
MATH	—	51.9
GSM8K	—	84.5

safety

Benchmark	Gemini 1.0 Pro	Llama 3.1 8B
TruthfulQA	—	52.4

Category Winners

coding

Llama 3.1 8B

8.1

math

Llama 3.1 8B

5.1

reasoning

Gemini 1.0 Pro

2.3

general

Llama 3.1 8B

4.4

language

Llama 3.1 8B

1.8

multimodal

Gemini 1.0 Pro

8.1

safety

Llama 3.1 8B

3.2