ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Nova Lite vs Qwen2.5 14B Instruct

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

Retired Qwen2.5 14B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    13/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
  2. Amazon

    Nova Lite

    Released Dec 3, 2024

    60/100
    • ECI—
    • Price$0.06 / $0.24
    • Context300K
  3. Alibaba (Qwen)

    Qwen2.5 14B Instruct

    Released Sep 2024Retired

    25/100
    • ECI—
    • Price$0.35 / $1.40
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Nova Lite 60/100, Qwen2.5 14B Instruct 25/100, Aya Expanse 32B 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceNova LiteNova Lite $0.105 · Qwen2.5 14B Instruct $0.613 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
  • Longest contextNova LiteNova Lite 300,000 · Qwen2.5 14B Instruct 131,072 · Aya Expanse 32B 128,000 tokens
  • Widest inputsNova LiteAya Expanse 32B: Text · Nova Lite: Text, Images, PDFs, Video · Qwen2.5 14B Instruct: Text
  • Self-hostingAya Expanse 32B and Qwen2.5 14B InstructPublishes downloadable weights (CC-BY-NC-4.0)
How the score is built
MeasureWeightAya Expanse 32BNova LiteQwen2.5 14B Instruct
Inputs & features60%07025
Context window40%324524
Specs only100%13/10060/10025/100

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 Nova Lite vs Qwen2.5 14B Instruct specifications side by side
SpecificationAya Expanse 32BCohereNova LiteAmazonQwen2.5 14B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50$0.06 (best)$0.35
Output$1.50$0.24 (best)$1.40
Cached input—$0.015—
Blended (3:1)$0.75$0.105 (best)$0.613
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIOfficial Amazon Bedrock APIOfficial Alibaba API
Limits
Context window128,000 tokens300,000 tokens (best)131,072 tokens
Max output4,000 tokens10,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoYesNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsOpenCC-BY-NC-4.0ProprietaryOpen
API model IDc4ai-aya-expanse-32bamazon.nova-lite-v1:0qwen2-5-14b-instruct
API providers28 (best)1
ReleasedOct 24, 2024Dec 3, 2024Sep 2024
Knowledge cutoff—Oct 2024Apr 2024
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
  • Nova Lite$1.08
  • Qwen2.5 14B Instruct$6.30
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Nova Lite or Qwen2.5 14B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Nova Lite 60/100, Qwen2.5 14B Instruct 25/100, Aya Expanse 32B 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Aya Expanse 32B, Nova Lite or Qwen2.5 14B Instruct?

Nova Lite is cheaper at $0.06 input / $0.24 output per million tokens (official Amazon Bedrock API price). Qwen2.5 14B Instruct costs $0.35 input / $1.40 output per million tokens (official Alibaba API price); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.105 per million tokens for Nova Lite versus $0.613 for Qwen2.5 14B Instruct (5.8× as much) and $0.75 for Aya Expanse 32B (7.1× 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, Nova Lite has not been scored yet and Qwen2.5 14B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aya Expanse 32B, Nova Lite and Qwen2.5 14B 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?

Nova Lite has the largest context window at 300,000 tokens, against 131,072 for Qwen2.5 14B Instruct and 128,000 for Aya Expanse 32B. Maximum output per response: Aya Expanse 32B up to 4,000, Nova Lite up to 10,000, Qwen2.5 14B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Nova Lite accepts text, images, PDFs and video; Qwen2.5 14B Instruct accepts text. Nova Lite handles the widest range of inputs.

Are any of these open source?

Aya Expanse 32B and Qwen2.5 14B Instruct publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Nova Lite is proprietary.

Which is newer?

Nova Lite is the newest, released Dec 3, 2024. Aya Expanse 32B came out Oct 24, 2024; Qwen2.5 14B Instruct came out Sep 2024. Knowledge cutoff: Nova Lite Oct 2024, Qwen2.5 14B Instruct Apr 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.