ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Nova Pro vs Mistral Large 2.1 vs Qwen2.5 32B Instruct

Nova Pro comes out ahead, 48 to 43 and 38 on our weighted score, though Qwen2.5 32B Instruct is 13% cheaper per token.

  1. Our pick

    Amazon

    Nova Pro

    Released Dec 3, 2024

    48/100
    • ECI123.8
    • Price$0.80 / $3.20
    • Context300K
    Full specs Remove Nova Pro

  2. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    38/100
    • ECI128.5
    • Price$2.00 / $6.00
    • Context131K
    Full specs Remove Mistral Large 2.1

  3. Alibaba (Qwen)

    Qwen2.5 32B Instruct

    Released Sep 17, 2024

    43/100
    • ECI128.5
    • Price$0.70 / $2.80
    • Context131K
    Full specs Remove Qwen2.5 32B Instruct
01 — Verdict

Nova Pro is our pick

Nova Pro is the better all-round choice, scoring 48/100 against Qwen2.5 32B Instruct (43) and Mistral Large 2.1 (38). It leads on inputs & features and context window. Qwen2.5 32B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Large 2.1 and Qwen2.5 32B InstructCapabilities Index (ECI): Mistral Large 2.1 128.5 · Qwen2.5 32B Instruct 128.5 · Nova Pro 123.8
  • Lowest priceQwen2.5 32B InstructQwen2.5 32B Instruct $1.23 · Nova Pro $1.40 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend)
  • Longest contextNova ProNova Pro 300,000 · Mistral Large 2.1 131,072 · Qwen2.5 32B Instruct 131,072 tokens
  • Widest inputsNova ProNova Pro: Text, Images, PDFs, Video · Mistral Large 2.1: Text · Qwen2.5 32B Instruct: Text
  • Self-hostingMistral Large 2.1 and Qwen2.5 32B InstructPublishes downloadable weights
How the score is built
MeasureWeightNova ProMistral Large 2.1Qwen2.5 32B Instruct
CapabilityCapabilities Index (ECI)50%455151
Price25%432746
Inputs & features15%702525
Context window10%392424
Overall100%48/10038/10043/100
02 — Side by side

Every spec in one table

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

Nova Pro vs Mistral Large 2.1 vs Qwen2.5 32B Instruct specifications side by side
SpecificationNova ProAmazonMistral Large 2.1Mistral AIQwen2.5 32B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)123.8128.5 (best)128.5 (best)
ECI rank#137 of 148#130 of 148 (best)#131 of 148
GPQA DiamondGraduate-level science questions—51.3% (best)46.1%
OTIS Mock AIME 2024–2025Competition mathematics—7.8% (best)7.4%
Price per million tokens
Input$0.80$2.00$0.70 (best)
Output$3.20$6.00$2.80 (best)
Cached input$0.20——
Blended (3:1)$1.40$3.00$1.23 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Amazon Bedrock APIOfficial Mistral APIOfficial Alibaba API
Limits
Context window300,000 tokens (best)131,072 tokens131,072 tokens
Max output10,000 tokens16,384 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoYesNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpen
API model IDamazon.nova-pro-v1:0mistral-large-2411qwen2-5-32b-instruct
API providers3 (best)21
ReleasedDec 3, 2024Nov 18, 2024Sep 17, 2024
Knowledge cutoffOct 2024Nov 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.

  • Nova Pro$14.40
  • Mistral Large 2.1$32.00
  • Qwen2.5 32B Instruct$12.60
04 — Questions

Which should you choose?

Which is better: Nova Pro, Mistral Large 2.1 or Qwen2.5 32B Instruct?

Nova Pro is the better all-round choice, scoring 48/100 against Qwen2.5 32B Instruct (43) and Mistral Large 2.1 (38). It leads on inputs & features and context window. Qwen2.5 32B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Nova Pro, Mistral Large 2.1 or Qwen2.5 32B Instruct?

Qwen2.5 32B Instruct is cheaper at $0.70 input / $2.80 output per million tokens (official Alibaba API price). Nova Pro costs $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $1.23 per million tokens for Qwen2.5 32B Instruct versus $1.40 for Nova Pro (1.1× as much) and $3.00 for Mistral Large 2.1 (2.4× as much).

Which scores higher on benchmarks?

Mistral Large 2.1 scores higher on the Capabilities Index (ECI): Mistral Large 2.1 128.5 (#130 of 148), Qwen2.5 32B Instruct 128.5 (#131 of 148) and Nova Pro 123.8 (#137 of 148). The confidence ranges of the top two overlap (123.8–130.8 vs 123.5–130.0), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for Nova Pro, Mistral Large 2.1 and Qwen2.5 32B Instruct yet, so there is no like-for-like coding score. On overall capability, Mistral Large 2.1 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

Nova Pro has the largest context window at 300,000 tokens, against 131,072 for Mistral Large 2.1 and 131,072 for Qwen2.5 32B Instruct. Maximum output per response: Nova Pro up to 10,000, Mistral Large 2.1 up to 16,384, Qwen2.5 32B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Nova Pro accepts text, images, PDFs and video; Mistral Large 2.1 accepts text; Qwen2.5 32B Instruct accepts text. Nova Pro handles the widest range of inputs.

Are any of these open source?

Mistral Large 2.1 and Qwen2.5 32B Instruct publishes its weights and can be self-hosted; Nova Pro is proprietary.

Which is newer?

Nova Pro is the newest, released Dec 3, 2024. Mistral Large 2.1 came out Nov 18, 2024; Qwen2.5 32B Instruct came out Sep 17, 2024. Knowledge cutoff: Nova Pro Oct 2024, Mistral Large 2.1 Nov 2024, Qwen2.5 32B Instruct Apr 2024.

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