ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Mistral Small 3.2 vs Qwen3 30B-A3B Instruct 2507 vs Gemma 3 27B IT

Qwen3 30B-A3B Instruct 2507 comes out ahead, 58 to 51 and 49 on our weighted score.

  1. Mistral AI

    Mistral Small 3.2

    Released Jun 20, 2025Deprecated

    51/100
    • ECI—
    • Price$0.10 / $0.30
    • Context128K
    Full specs Remove Mistral Small 3.2
  2. Our pick

    Alibaba (Qwen)

    Qwen3 30B-A3B Instruct 2507

    Released Jul 28, 2025

    58/100
    • ECI137.3
    • Price$0.10 / $0.30
    • Context262K
    Full specs Remove Qwen3 30B-A3B Instruct 2507

  3. Google

    Gemma 3 27B IT

    Released Mar 12, 2025

    49/100
    • ECI129.9
    • Price$0.11 / $0.30
    • Context131K
    Full specs Remove Gemma 3 27B IT
01 — Verdict

Qwen3 30B-A3B Instruct 2507 is our pick

Qwen3 30B-A3B Instruct 2507 is the better all-round choice, scoring 58/100 against Mistral Small 3.2 (51) and Gemma 3 27B IT (49). It leads on capability and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Small 3.2 has no Capabilities Index score yet.

  • CapabilityQwen3 30B-A3B Instruct 2507Shared benchmarks: Qwen3 30B-A3B Instruct 2507 58.9% · Mistral Small 3.2 39.7% · Gemma 3 27B IT 35.1%
  • Lowest priceMistral Small 3.2 and Qwen3 30B-A3B Instruct 2507Mistral Small 3.2 $0.15 · Qwen3 30B-A3B Instruct 2507 $0.15 · Gemma 3 27B IT $0.157 per 1M tokens (3:1 blend)
  • Longest contextQwen3 30B-A3B Instruct 2507Qwen3 30B-A3B Instruct 2507 262,144 · Gemma 3 27B IT 131,072 · Mistral Small 3.2 128,000 tokens
  • Widest inputsMistral Small 3.2 and Gemma 3 27B ITMistral Small 3.2: Text, Images · Qwen3 30B-A3B Instruct 2507: Text · Gemma 3 27B IT: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightMistral Small 3.2Qwen3 30B-A3B Instruct 2507Gemma 3 27B IT
CapabilityShared benchmarks50%405935
Price25%858584
Inputs & features15%502550
Context window10%243725
Overall100%51/10058/10049/100
02 — Side by side

Every spec in one table

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

Mistral Small 3.2 vs Qwen3 30B-A3B Instruct 2507 vs Gemma 3 27B IT specifications side by side
SpecificationMistral Small 3.2Mistral AIQwen3 30B-A3B Instruct 2507Alibaba (Qwen)Gemma 3 27B ITGoogle
Capability
Capabilities Index (ECI)—137.3 (best)129.9
ECI rank—#124 of 165 (best)#137 of 165
GPQA DiamondGraduate-level science questions49.1%55.6% (best)47.7%
OTIS Mock AIME 2024–2025Competition mathematics30.3%62.2% (best)22.5%
Price per million tokens
Input$0.10 (best)$0.10 (best)$0.11
Output$0.30$0.30$0.30 (best)
Cached input———
Blended (3:1)$0.15 (best)$0.15 (best)$0.157
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 12 providersMedian of 16 providers
Limits
Context window128,000 tokens262,144 tokens (best)131,072 tokens
Max output16,384 tokens16,384 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenApache 2.0Open
API model IDmistral-small-2506——
API providers71417 (best)
ReleasedJun 20, 2025Jul 28, 2025Mar 12, 2025
Knowledge cutoffMar 2025—Aug 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 Small 3.2$1.60
  • Qwen3 30B-A3B Instruct 2507$1.60
  • Gemma 3 27B IT$1.69
04 — Questions

Which should you choose?

Which is better: Mistral Small 3.2, Qwen3 30B-A3B Instruct 2507 or Gemma 3 27B IT?

Qwen3 30B-A3B Instruct 2507 is the better all-round choice, scoring 58/100 against Mistral Small 3.2 (51) and Gemma 3 27B IT (49). It leads on capability and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Small 3.2 has no Capabilities Index score yet.

Which is cheaper, Mistral Small 3.2, Qwen3 30B-A3B Instruct 2507 or Gemma 3 27B IT?

Mistral Small 3.2 is cheaper at $0.10 input / $0.30 output per million tokens (official Mistral API price). Qwen3 30B-A3B Instruct 2507 costs $0.10 input / $0.30 output per million tokens (median across 12 API providers); Gemma 3 27B IT costs $0.11 input / $0.30 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Mistral Small 3.2 versus $0.15 for Qwen3 30B-A3B Instruct 2507 (1× as much) and $0.157 for Gemma 3 27B IT (1× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Qwen3 30B-A3B Instruct 2507 58.9%, Mistral Small 3.2 39.7% and Gemma 3 27B IT 35.1%. On individual benchmarks: GPQA Diamond — Qwen3 30B-A3B Instruct 2507 55.6%, Mistral Small 3.2 49.1%, Gemma 3 27B IT 47.7%; OTIS Mock AIME 2024–2025 — Qwen3 30B-A3B Instruct 2507 62.2%, Mistral Small 3.2 30.3%, Gemma 3 27B IT 22.5%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Small 3.2, Qwen3 30B-A3B Instruct 2507 and Gemma 3 27B IT yet, so there is no like-for-like coding score. On overall capability, Qwen3 30B-A3B Instruct 2507 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?

Qwen3 30B-A3B Instruct 2507 has the largest context window at 262,144 tokens, against 131,072 for Gemma 3 27B IT and 128,000 for Mistral Small 3.2. Maximum output per response: Mistral Small 3.2 up to 16,384, Qwen3 30B-A3B Instruct 2507 up to 16,384, Gemma 3 27B IT up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Mistral Small 3.2 accepts text and images; Qwen3 30B-A3B Instruct 2507 accepts text; Gemma 3 27B IT accepts text and images. Mistral Small 3.2 handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (Apache 2.0), so you can self-host them.

Which is newer?

Qwen3 30B-A3B Instruct 2507 is the newest, released Jul 28, 2025. Mistral Small 3.2 came out Jun 20, 2025; Gemma 3 27B IT came out Mar 12, 2025. Knowledge cutoff: Mistral Small 3.2 Mar 2025, Gemma 3 27B IT Aug 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons