ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Aya Expanse 32B vs Llama-3.1-8B-Instruct vs Qwen2.5-Coder-32B-Instruct

Llama-3.1-8B-Instruct comes out ahead, 56 to 45 and 33 on our weighted score, and it is the cheaper option too.

  1. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    33/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
    Full specs Remove Aya Expanse 32B
  2. Our pick

    Meta

    Llama-3.1-8B-Instruct

    Released Jul 23, 2024

    56/100
    • ECI116.6
    • Price$0.152 / $0.167
    • Context128K
    Full specs Remove Llama-3.1-8B-Instruct

  3. Alibaba (Qwen)

    Qwen2.5-Coder-32B-Instruct

    Released Nov 12, 2024

    45/100
    • ECI—
    • Price$0.43 / $0.60
    • Context131K
    Full specs Remove Qwen2.5-Coder-32B-Instruct
01 — Verdict

Llama-3.1-8B-Instruct is our pick

Llama-3.1-8B-Instruct is the better all-round choice, scoring 56/100 against Qwen2.5-Coder-32B-Instruct (45) and Aya Expanse 32B (33). It leads on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceLlama-3.1-8B-InstructLlama-3.1-8B-Instruct $0.156 · Qwen2.5-Coder-32B-Instruct $0.473 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct 131,072 · Aya Expanse 32B 128,000 · Llama-3.1-8B-Instruct 128,000 tokens
  • Widest inputsSame inputsAya Expanse 32B: Text · Llama-3.1-8B-Instruct: Text · Qwen2.5-Coder-32B-Instruct: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightAya Expanse 32BLlama-3.1-8B-InstructQwen2.5-Coder-32B-Instruct
Price50%568865
Inputs & features30%02525
Context window20%242424
Overall100%33/10056/10045/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Aya Expanse 32B vs Llama-3.1-8B-Instruct vs Qwen2.5-Coder-32B-Instruct specifications side by side
SpecificationAya Expanse 32BCohereLlama-3.1-8B-InstructMetaQwen2.5-Coder-32B-InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)—116.6—
ECI rank—#145 of 148—
GPQA DiamondGraduate-level science questions—27.0%—
OTIS Mock AIME 2024–2025Competition mathematics—1.7%—
Price per million tokens
Input$0.50$0.152 (best)$0.43
Output$1.50$0.167 (best)$0.60
Cached input———
Blended (3:1)$0.75$0.156 (best)$0.473
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 9 providersMedian of 4 providers
Limits
Context window128,000 tokens128,000 tokens131,072 tokens (best)
Max output4,000 tokens4,096 tokens8,192 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsOpenCC-BY-NC-4.0OpenOpen
API model IDc4ai-aya-expanse-32b——
API providers29 (best)4
ReleasedOct 24, 2024Jul 23, 2024Nov 12, 2024
Knowledge cutoff—Dec 2023—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Aya Expanse 32B$8.00
  • Llama-3.1-8B-Instruct$1.85
  • Qwen2.5-Coder-32B-Instruct$5.50
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Llama-3.1-8B-Instruct or Qwen2.5-Coder-32B-Instruct?

Llama-3.1-8B-Instruct is the better all-round choice, scoring 56/100 against Qwen2.5-Coder-32B-Instruct (45) and Aya Expanse 32B (33). It leads on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Aya Expanse 32B, Llama-3.1-8B-Instruct or Qwen2.5-Coder-32B-Instruct?

Llama-3.1-8B-Instruct is cheaper at $0.152 input / $0.167 output per million tokens (median across 9 API providers). Qwen2.5-Coder-32B-Instruct costs $0.43 input / $0.60 output per million tokens (median across 4 API providers); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.156 per million tokens for Llama-3.1-8B-Instruct versus $0.473 for Qwen2.5-Coder-32B-Instruct (3× as much) and $0.75 for Aya Expanse 32B (4.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Llama-3.1-8B-Instruct has an ECI of 116.6 and Qwen2.5-Coder-32B-Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aya Expanse 32B, Llama-3.1-8B-Instruct and Qwen2.5-Coder-32B-Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen2.5-Coder-32B-Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 128,000 for Llama-3.1-8B-Instruct. Maximum output per response: Aya Expanse 32B up to 4,000, Llama-3.1-8B-Instruct up to 4,096, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Llama-3.1-8B-Instruct accepts text; Qwen2.5-Coder-32B-Instruct accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.

Which is newer?

Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Aya Expanse 32B came out Oct 24, 2024; Llama-3.1-8B-Instruct came out Jul 23, 2024. Knowledge cutoff: Llama-3.1-8B-Instruct Dec 2023.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons