ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Mistral Large 2.1 vs Nova Pro vs Qwen2.5 72B Instruct

Nova Pro comes out ahead, 48 to 40 and 38 on our weighted score, and it is the cheaper option too.

  1. 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
  2. Our pick

    Amazon

    Nova Pro

    Released Dec 3, 2024

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

  3. Alibaba (Qwen)

    Qwen2.5 72B Instruct

    Released Sep 19, 2024

    40/100
    • ECI129.0
    • Price$1.40 / $5.60
    • Context131K
    Full specs Remove Qwen2.5 72B Instruct
01 — Verdict

Nova Pro is our pick

Nova Pro is the better all-round choice, scoring 48/100 against Qwen2.5 72B Instruct (40) and Mistral Large 2.1 (38). It leads on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen2.5 72B InstructCapabilities Index (ECI): Qwen2.5 72B Instruct 129.0 · Mistral Large 2.1 128.5 · Nova Pro 123.8
  • Lowest priceNova ProNova Pro $1.40 · Qwen2.5 72B Instruct $2.45 · 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 72B Instruct 131,072 tokens
  • Widest inputsNova ProMistral Large 2.1: Text · Nova Pro: Text, Images, PDFs, Video · Qwen2.5 72B Instruct: Text
  • Self-hostingMistral Large 2.1 and Qwen2.5 72B InstructPublishes downloadable weights
How the score is built
MeasureWeightMistral Large 2.1Nova ProQwen2.5 72B Instruct
CapabilityCapabilities Index (ECI)50%514552
Price25%274331
Inputs & features15%257025
Context window10%243924
Overall100%38/10048/10040/100
02 — Side by side

Every spec in one table

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

Mistral Large 2.1 vs Nova Pro vs Qwen2.5 72B Instruct specifications side by side
SpecificationMistral Large 2.1Mistral AINova ProAmazonQwen2.5 72B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)128.5123.8129.0 (best)
ECI rank#130 of 148#137 of 148#128 of 148 (best)
GPQA DiamondGraduate-level science questions51.3% (best)—49.2%
OTIS Mock AIME 2024–2025Competition mathematics7.8%—8.1% (best)
Price per million tokens
Input$2.00$0.80 (best)$1.40
Output$6.00$3.20 (best)$5.60
Cached input—$0.20—
Blended (3:1)$3.00$1.40 (best)$2.45
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Amazon Bedrock APIOfficial Alibaba API
Limits
Context window131,072 tokens300,000 tokens (best)131,072 tokens
Max output16,384 tokens (best)10,000 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoYesNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpen
API model IDmistral-large-2411amazon.nova-pro-v1:0qwen2-5-72b-instruct
API providers23 (best)1
ReleasedNov 18, 2024Dec 3, 2024Sep 19, 2024
Knowledge cutoffNov 2024Oct 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.

  • Mistral Large 2.1$32.00
  • Nova Pro$14.40
  • Qwen2.5 72B Instruct$25.20
04 — Questions

Which should you choose?

Which is better: Mistral Large 2.1, Nova Pro or Qwen2.5 72B Instruct?

Nova Pro is the better all-round choice, scoring 48/100 against Qwen2.5 72B Instruct (40) and Mistral Large 2.1 (38). It leads on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Mistral Large 2.1, Nova Pro or Qwen2.5 72B Instruct?

Nova Pro is cheaper at $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price). Qwen2.5 72B Instruct costs $1.40 input / $5.60 output per million tokens (official Alibaba 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 $1.40 per million tokens for Nova Pro versus $2.45 for Qwen2.5 72B Instruct (1.8× as much) and $3.00 for Mistral Large 2.1 (2.1× as much).

Which scores higher on benchmarks?

Qwen2.5 72B Instruct scores higher on the Capabilities Index (ECI): Qwen2.5 72B Instruct 129.0 (#128 of 148), Mistral Large 2.1 128.5 (#130 of 148) and Nova Pro 123.8 (#137 of 148). The confidence ranges of the top two overlap (123.8–130.7 vs 123.8–130.8), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Large 2.1, Nova Pro and Qwen2.5 72B Instruct yet, so there is no like-for-like coding score. On overall capability, Qwen2.5 72B Instruct 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 72B Instruct. Maximum output per response: Mistral Large 2.1 up to 16,384, Nova Pro up to 10,000, Qwen2.5 72B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Mistral Large 2.1 accepts text; Nova Pro accepts text, images, PDFs and video; Qwen2.5 72B Instruct accepts text. Nova Pro handles the widest range of inputs.

Are any of these open source?

Mistral Large 2.1 and Qwen2.5 72B 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 72B Instruct came out Sep 19, 2024. Knowledge cutoff: Mistral Large 2.1 Nov 2024, Nova Pro Oct 2024, Qwen2.5 72B 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