ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Mistral Nemo vs Qwen2.5 32B Instruct vs Qwen2.5 7B Instruct

Mistral Nemo comes out ahead, 48 to 44 and 43 on our weighted score, and it is the cheaper option too.

  1. Our pick

    Mistral AI

    Mistral Nemo

    Released Jul 1, 2024

    48/100
    • ECI118.7
    • Price$0.15 / $0.15
    • Context128K
  2. Alibaba (Qwen)

    Qwen2.5 32B Instruct

    Released Sep 17, 2024

    43/100
    • ECI128.5
    • Price$0.70 / $2.80
    • Context131K
  3. Alibaba (Qwen)

    Qwen2.5 7B Instruct

    Released Sep 19, 2024

    44/100
    • ECI118.5
    • Price$0.175 / $0.70
    • Context131K
01 — Verdict

Mistral Nemo is our pick

Mistral Nemo is the better all-round choice, scoring 48/100 against Qwen2.5 7B Instruct (44) and Qwen2.5 32B Instruct (43). It leads on price. Qwen2.5 32B Instruct wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen2.5 32B InstructCapabilities Index (ECI): Qwen2.5 32B Instruct 128.5 · Mistral Nemo 118.7 · Qwen2.5 7B Instruct 118.5
  • Lowest priceMistral NemoMistral Nemo $0.15 · Qwen2.5 7B Instruct $0.306 · Qwen2.5 32B Instruct $1.23 per 1M tokens (3:1 blend)
  • Longest contextQwen2.5 32B Instruct and Qwen2.5 7B InstructQwen2.5 32B Instruct 131,072 · Qwen2.5 7B Instruct 131,072 · Mistral Nemo 128,000 tokens
  • Widest inputsSame inputsMistral Nemo: Text · Qwen2.5 32B Instruct: Text · Qwen2.5 7B Instruct: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightMistral NemoQwen2.5 32B InstructQwen2.5 7B Instruct
CapabilityCapabilities Index (ECI)50%395138
Price25%894674
Inputs & features15%252525
Context window10%242424
Overall100%48/10043/10044/100
02 — Side by side

Every spec in one table

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

Mistral Nemo vs Qwen2.5 32B Instruct vs Qwen2.5 7B Instruct specifications side by side
SpecificationMistral NemoMistral AIQwen2.5 32B InstructAlibaba (Qwen)Qwen2.5 7B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)118.7128.5 (best)118.5
ECI rank#140 of 148#131 of 148 (best)#141 of 148
GPQA DiamondGraduate-level science questions29.9%46.1% (best)35.5%
OTIS Mock AIME 2024–2025Competition mathematics—7.4% (best)2.5%
Price per million tokens
Input$0.15 (best)$0.70$0.175
Output$0.15 (best)$2.80$0.70
Cached input———
Blended (3:1)$0.15 (best)$1.23$0.306
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Alibaba APIOfficial Alibaba API
Limits
Context window128,000 tokens131,072 tokens (best)131,072 tokens (best)
Max output128,000 tokens (best)8,192 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model IDmistral-nemoqwen2-5-32b-instructqwen2-5-7b-instruct
API providers5 (best)11
ReleasedJul 1, 2024Sep 17, 2024Sep 19, 2024
Knowledge cutoffJul 2024Apr 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 Nemo$1.80
  • Qwen2.5 32B Instruct$12.60
  • Qwen2.5 7B Instruct$3.15
04 — Questions

Which should you choose?

Which is better: Mistral Nemo, Qwen2.5 32B Instruct or Qwen2.5 7B Instruct?

Mistral Nemo is the better all-round choice, scoring 48/100 against Qwen2.5 7B Instruct (44) and Qwen2.5 32B Instruct (43). It leads on price. Qwen2.5 32B Instruct wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Mistral Nemo, Qwen2.5 32B Instruct or Qwen2.5 7B Instruct?

Mistral Nemo is cheaper at $0.15 input / $0.15 output per million tokens (official Mistral API price). Qwen2.5 7B Instruct costs $0.175 input / $0.70 output per million tokens (official Alibaba API price); Qwen2.5 32B Instruct costs $0.70 input / $2.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Mistral Nemo versus $0.306 for Qwen2.5 7B Instruct (2× as much) and $1.23 for Qwen2.5 32B Instruct (8.2× as much).

Which scores higher on benchmarks?

Qwen2.5 32B Instruct scores higher on the Capabilities Index (ECI): Qwen2.5 32B Instruct 128.5 (#131 of 148), Mistral Nemo 118.7 (#140 of 148) and Qwen2.5 7B Instruct 118.5 (#141 of 148). Their confidence ranges do not overlap (123.5–130.0 vs 111.3–121.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — Qwen2.5 32B Instruct 46.1%, Qwen2.5 7B Instruct 35.5%, Mistral Nemo 29.9%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Nemo, Qwen2.5 32B Instruct and Qwen2.5 7B Instruct yet, so there is no like-for-like coding score. On overall capability, Qwen2.5 32B 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?

Qwen2.5 32B Instruct and Qwen2.5 7B Instruct have the largest context windows (131,072 and 131,072 tokens), against 128,000 for Mistral Nemo. Maximum output per response: Mistral Nemo up to 128,000, Qwen2.5 32B Instruct up to 8,192, Qwen2.5 7B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Mistral Nemo accepts text; Qwen2.5 32B Instruct accepts text; Qwen2.5 7B Instruct accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Qwen2.5 7B Instruct is the newest, released Sep 19, 2024. Qwen2.5 32B Instruct came out Sep 17, 2024; Mistral Nemo came out Jul 1, 2024. Knowledge cutoff: Mistral Nemo Jul 2024, Qwen2.5 32B Instruct Apr 2024, Qwen2.5 7B 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.