WritingmateWritingmate
Model Comparison

Llama 3.2 1B Instruct vs Perceptron Mk1.5Which Is Better in 2026?

Meta: Llama 3.2 1B Instruct logoMeta•
Perceptron

Llama 3.2 1B Instruct vs Perceptron Mk1.5: which should you choose in 2026?

Llama 3.2 1B Instruct (by Meta) and Perceptron Mk1.5 (by Perceptron) are compared below. Here is how they stack up on benchmarks, price, and capabilities, and which one to pick in 2026.

There are not enough shared, protocol-compatible benchmark results to declare a performance leader.

Llama 3.2 1B Instruct is about 6.9× cheaper on a blended 3:1 input/output basis ($0.0705 vs $0.4875 per 1M tokens).

Llama 3.2 1B Instruct has the larger context window (60,000 tokens vs 36,864 tokens).

Choose Llama 3.2 1B Instruct if…

  • • lower blended API cost matters for your workload
  • • you work with longer documents, transcripts, or codebases

Choose Perceptron Mk1.5 if…

  • • you need a model with explicit reasoning support
  • • you need image inputs

The benchmark count includes only results measured with a matching benchmark version and protocol. Arena scores are shown separately. Missing, preliminary, and incompatible data is not treated as a controlled win. Published point-score comparisons are labeled separately when protocol details are incomplete. For text-output models, the verdict also compares token pricing and context windows.

Chat with both models
vs

Performance benchmarks

Every value links to its source. A dash means that no reviewed result is available for that exact model and protocol.

Llama 3.2 1B Instruct and Perceptron Mk1.5 benchmark results
BenchmarkLlama 3.2 1B InstructPerceptron Mk1.5
AutomationBench-AA

A 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework.

Guardrail-aware score

——
BrowseComp

A benchmark of difficult, verifiable information-seeking questions designed to measure an agent's ability to locate hard-to-find facts through web browsing.

Accuracy

——
OSWorld-Verified

A verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state.

Mean task reward

——
SWE-Bench Verified

A human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests.

Resolved

——
Terminal-Bench 2.1

Version 2.1 of the benchmark for completing realistic tasks in terminal environments. Harness, resource limits, and attempt count are part of the protocol.

Mean task success

——
AutoBench

A dynamic LLM evaluation framework in which models generate questions, answer them, and participate in reciprocal peer assessment. AutoBench is distinct from Zapier's AutomationBench.

Weighted peer-assessment score

——
GPQA Diamond

The highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry.

Accuracy

——
Humanity's Last Exam

A 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged.

Accuracy

——
Arena preference scores
Arena (Text)

Human preference score

1111 ±8
—

Benchmark sources

Reviewed evidence last updated 2026-08-09. Arena data last refreshed Oct 2, 2026.

Pricing, capabilities, and model facts

Llama 3.2 1B Instruct and Perceptron Mk1.5 model facts
FeatureLlama 3.2 1B InstructPerceptron Mk1.5
Context & model facts
DeveloperMetaPerceptron
API providerMetaPerceptron
Input context60,000 tokens36,864 tokens
Maximum output54,000 tokens8,192 tokens
Released——
Added to WritingmateSep 25, 2024Sep 25, 2026
LicenseNot availableNot available
Knowledge cutoff2023-12-31—
Capabilities
InputsTextText, Image, Video, Audio
OutputsTextText
Provider endpoint accepts tool parametersNoYes
ReasoningNoYes
VisionNoYes
Image GenerationNoNo
Video GenerationNoNo
API pricing
Input (per 1M tokens)$0.027$0.15
Output (per 1M tokens)$0.201$1.50
Blended 3:1 input/output$0.0705$0.4875
API performance
p95 latencyNot measuredNot measured
Output throughputNot measuredNot measured
Writingmate shows API performance only when both models have enough observations from the same measurement window, prompt profile, and provider. Third-party latency values are not copied into this table.

Data sources

  • Writingmate model catalog (pricing, limits, and availability)

Catalog data last updated Sep 25, 2026.

Why Pay for Multiple Subscriptions?

Comparing Llama 3.2 1B Instruct from Meta with Perceptron Mk1.5 from Perceptron? Instead of managing separate API keys and subscriptions, get both with Writingmate.

Subscription-plan access for Llama 3.2 1B Instruct and Perceptron Mk1.5
PlanPriceLlama 3.2 1B InstructPerceptron Mk1.5AI ImagesAI Video
Writingmate Pro
Most popular
$20/moIncludedIncludedNano Banana Pro, FLUX.2, DALL-E & moreVEO 3.1, Kling 3.0
Writingmate Ultimate
Power users
$60/moIncludedIncludedNano Banana Pro, FLUX.2, DALL-E & moreVEO 3.1, Kling 3.0
View Plans & Pricing

Llama 3.2 1B Instruct vs Perceptron Mk1.5 FAQ

Which is better, Llama 3.2 1B Instruct or Perceptron Mk1.5?

There are not enough shared, protocol-compatible benchmark results to declare a performance leader. Llama 3.2 1B Instruct is about 6.9× cheaper on a blended 3:1 input/output basis ($0.0705 vs $0.4875 per 1M tokens). Llama 3.2 1B Instruct has the larger context window (60,000 tokens vs 36,864 tokens).

Which model is cheaper to use through an API?

Llama 3.2 1B Instruct is about 6.9× cheaper on a blended 3:1 input/output basis ($0.0705 vs $0.4875 per 1M tokens).

Which model supports more context?

Llama 3.2 1B Instruct has the larger context window (60,000 tokens vs 36,864 tokens).

Can I switch between Llama 3.2 1B Instruct and Perceptron Mk1.5?

Yes. Use the model selector on this page to open any current Writingmate model comparison. You can also run the same prompt with both models in Writingmate.