Language modelActive

Llama 3.3 70B

Specifications and access

Specification	Value and source
Weights	Open weightsSource not specified
Access	API, LocalSource
Parameters	70BSource not specified
Context window	131,072 tokensSource
Knowledge cutoff	December 2023Source
License	Llama 3.3 Community LicenseSource
Release	2024-12-06Source
Parameters	70 BSource
Architecture	dense transformerSource
Input	TextSource
Output	Text, codeSource
Training tokens	15T+Source
Knowledge cutoff	2023-12Source

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

MMLU CoT (Show measurement, test conditions, and source)

Source value: 86
Score: 86
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table; chain-of-thought setting as labeled

Source Meta Llama 3.3 model card

MMLU Pro (Show measurement, test conditions, and source)

Source value: 68.9
Score: 68.9
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

IFEval (Show measurement, test conditions, and source)

Source value: 92.1
Score: 92.1
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

GPQA Diamond (Show measurement, test conditions, and source)

Source value: 50.5
Score: 50.5
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

HumanEval (Show measurement, test conditions, and source)

Source value: 88.4
Score: 88.4
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

MBPP (Show measurement, test conditions, and source)

Source value: 87.6
Score: 87.6
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

MATH (Show measurement, test conditions, and source)

Source value: 77
Score: 77
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

BFCLv2 (Show measurement, test conditions, and source)

Source value: 77.3
Score: 77.3
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

MGSM (Show measurement, test conditions, and source)

Source value: 91.1
Score: 91.1
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Meta Llama 3.3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned table; Card benchmark table

Source Meta Llama 3.3 model card

Artificial Analysis Intelligence Index (Show measurement, test conditions, and source)

Source value: 7.66380859299009
Score: 7.66380859299009
Metric: points
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown

Source Artificial Analysis

AA-Omniscience Index (Show measurement, test conditions, and source)

Source value: -54.1666666666667
Score: -54.1666666666667
Metric: points
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown

Source Artificial Analysis

Output speed (Show measurement, test conditions, and source)

Source value: 88.5604020209479
Score: 88.5604020209479
Metric: tokens/s
Unit: tokens/s
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.

Source Artificial Analysis

Page 1 of 2

Predecessor and successor

Earlier model generation: Llama 3.1 70B
Previous generation in the directory
Model lineage evidence
Meta's own model card places 'Llama 3.1 70B Instruct' directly beside 'Llama-3.3 70B Instruct' in its benchmark comparison table as the same-tier prior release; no explicit prose 'replaces' statement was found.
Meta, Llama-3.3-70B-Instruct model card (Hugging Face) (2026-09-19)
Later model generation: Llama 4 Maverick
Next generation in the directory
Model lineage evidence
Meta's official Llama 4 launch blog states 'Llama 4 Maverick offers high quality at a lower price compared to Llama 3.3 70B' and that the Llama 4 models are 'more powerful than all previous generation Llama models'.
Meta AI, "The Llama 4 herd" (2026-09-19)

Sources and data date

Type	Evidence and data date
Speed	Median across serving providers. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Meta Llama 3.3 model card (retrieved September 8, 2026) · Meta Llama 3.3 model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Meta Llama 3.3 model card (retrieved September 8, 2026) · Meta Llama 3.3 model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	max-output-tokens Original wording No model-specific maximum output in card.
Additional source	Context window data
Additional source	Knowledge cutoff data · Meta Llama model documentation · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0
Additional source	Meta, Llama-3.3-70B-Instruct model card (Hugging Face) (2026-09-19)
Additional source	Meta AI, "The Llama 4 herd" (2026-09-19)

Llama 3.3 70B

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date