> Llama 3.3 70B is an open-weights AI model from Meta, released 6 Dec 2024. Index score 106 (GPT-4 = 100), rank 173 of 229 ranked models. API price $0.10 in / $0.32 out per million tokens, 131K context.

[Models](https://themodelindex.org/models/) /[Meta](https://themodelindex.org/labs/meta/)

# Llama 3.3 70B

Meta

Released 6 Dec 2024

Open

[Compare](https://themodelindex.org/compare/llama-3-3-70b-vs-o1/) [Announcement](https://about.fb.com/ltam/news/2024/12/el-futuro-de-la-ia-construido-con-llama/)

10694–117

Index score

#173 of 229 models

1/ 8

Core tests taken

1 of 6 areas · plus 9 anchor tests

−30

Versus the frontier at release

best then: o1

$0.10/ $0.32

Price per million tokens

input / output, list price

131K

Context window

tokens it reads at once

## Where it sits · on the frontier

_Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_

GPT-4 Turbo (Apr 2024) reached this score 8 months earlier.

## Test results · by area · tick = best by any model

Show 8 anchor tests

Reasoning & knowledge

evidence

GPQA Diamond

47%

Humanity's Last Exam

no result

Maths

evidence

FrontierMath T1-3

no result

Coding

evidence

SWE-bench Verified

no result

Terminal-Bench

no result

Agents

evidence

APEX-Agents

no result

Novel problems

no evidence yet

ARC-AGI-2

no result

Long tasks

no evidence yet

METR time horizon

no result

Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above.

## What others say · rank on each leaderboard

The Model Index

independent tests, our method

#173

of 219 · 106

LMArena · Creative writing

creative writing

#231

of 386 · 1285

Epoch Capabilities Index

overall capability from many benchmarks

#144

of 239 · 127.3

LMArena · Text

overall chat quality, judged by people

#238

of 388 · 1318

LMArena · Maths

maths questions in chat

#230

of 373 · 1296

LMArena · Coding

coding questions in chat

#250

of 383 · 1346

Artificial Analysis Intelligence Index

overall capability across ten evaluations

#142

of 207 · 8

Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source.

## Best at · top three among current models

Not in the top three among current models on any category we track.

Where this model places in the top three of today's models, on category leaderboards and on our core tests.

## Where to use it · prices checked 1 Oct 2026

#### API providers · 10 · per million tokens, in / out

D

DeepInfra

$0.10 / $0.32 · fp8

cheapest

N

Novita

$0.14 / $0.40 · bf16

↗

A

AkashML

$0.20 / $0.52 · fp8

↗

P

Parasail

$0.22 / $0.50 · fp8

↗

S

SambaNova

$0.45 / $0.90

↗

G

Groq

$0.59 / $0.79

↗

C

CoreWeave

$0.71 / $0.71 · fp16

↗

G

Google

$0.72 / $0.72

↗

#### Run it yourself

🤗

Official weights

meta-llama/Llama-3.3-70B-Instruct

↗

Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps.

## Facts and sources

Released

6 Dec 2024

Announcement

[about.fb.com ↗](https://about.fb.com/ltam/news/2024/12/el-futuro-de-la-ia-construido-con-llama/)

Release entry

Llama 3.3 70B

Scored as

Llama 3.3 70B

Artificial Analysis index

8 (their estimate)

Output speed

82 tokens/s

Hugging Face

[meta-llama/Llama-3.3-70B-Instruct ↗](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)

## Meta releases · around this one

Llama 3.1

Open

23 JUL 2024

index 108

Llama 3.2

Open

25 SEP 2024

index 103

Llama 3.3 70B

Open

6 DEC 2024

index 106

Llama 4 Maverick

Open

5 APR 2025

index 115

Llama 4 Scout

Open

5 APR 2025

index 111

---
Source: https://themodelindex.org/models/llama-3-3-70b/ · The Model Index · data as of 2026-10-01