Llama 3.2 3B: Benchmarks, Pricing & Comparison

No published category-wide ranking is available for this model.

Entries 1-12 of 15. Page 1 of 2.

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 instruct (Show measurement, test conditions, and source)

Source value: 63.4
Score: 63.4
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:0
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

OpenRewrite (Show measurement, test conditions, and source)

Source value: 40.1
Score: 40.1
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:1
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

TLDR (Show measurement, test conditions, and source)

Source value: 19
Score: 19
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:2
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

IFEval (Show measurement, test conditions, and source)

Source value: 77.4
Score: 77.4
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:3
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

GSM8K (Show measurement, test conditions, and source)

Source value: 77.7
Score: 77.7
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:4
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

MATH (Show measurement, test conditions, and source)

Source value: 48
Score: 48
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:5
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

ARC instruct (Show measurement, test conditions, and source)

Source value: 78.6
Score: 78.6
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:6
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

GPQA (Show measurement, test conditions, and source)

Source value: 32.8
Score: 32.8
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:7
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

HellaSwag (Show measurement, test conditions, and source)

Source value: 69.8
Score: 69.8
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:8
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

BFCL (Show measurement, test conditions, and source)

Source value: 67
Score: 67
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:9
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

Nexus (Show measurement, test conditions, and source)

Source value: 34.3
Score: 34.3
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:10
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

InfiniteBench QA (Show measurement, test conditions, and source)

Source value: 19.8
Score: 19.8
Metric: percent
Unit: %
Direction: Higher is better
Comparison cohort: research:llama-3.2-3b:11
Source type: vendor-reported
Evaluator: Meta Llama 3.2 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruction-tuned BF16 table; shots per card

Source Meta Llama 3.2 model card

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Llama 3.2 3B

Not tested yet

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

Profile

Specifications and access

Published information about this model. Existing estimates are explicitly labeled.

Weights: Open weightsSource
Access: APISource
Parameters: 3.2BSource
Context window: 131,072 tokensSource
Knowledge cutoff: December 2023Source

Additional source observations

Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.

License: Llama 3.2 Community LicenseSource
Release: 2024-10-24Source
Parameters: 3.21 BSource
Architecture: dense transformerSource
Context window: 131,072 tokensSource
Input: TextSource
Output: Text, codeSource
Languages: 8Source
Training tokens: up to 9TSource
Knowledge cutoff: 2023-12Source

Pricing

Published prices

Prices apply to the stated unit. Resolution, output length, and provider can change the cost.

API input: $0.05 per 1M tokensSource
API output: $0.33 per 1M tokensSource

Cost example

100 API requests

$0.0215

100 requests with 1,000 input and 500 output tokens each calculate to $0.0215. Input accounts for $0.005; output accounts for $0.0165.

Input price: $0.05 / 1M tokensBase tier for each request
Output price: $0.33 / 1M tokensBase tier for each request

The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.

Open source

Head-to-head comparisons

Compare this model

Each matchup compares this model with exactly one other model from the same category.

There are no published direct comparisons for this model yet.

More models

Models from the same selection

All AI models

Llama 3.2 1B

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Price: Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
Pricing
Input: Documented modalities. Retrieved September 8, 2026.
Model documentation
Output: Documented modalities. Retrieved September 8, 2026.
Model documentation

Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.

Open evidence questions and research notes (original wording)

Not found in the inspected sources

max-output-tokens. No model-specific maximum output in the card.

Unresolved

AA benchmark rows. No exact Artificial Analysis model page located in the checked public sitemap.

Model metadataSource
Context window dataSource
Knowledge cutoff data (retrieved September 8, 2026)Source
API pricingSource