ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Magistral Small vs Qwen3 30B A3B vs GPT-4.1 mini

Too close to call on our weighted score (GPT-4.1 mini 59, Qwen3 30B A3B 57, Magistral Small 49). The right pick depends on what you value most.

  1. Mistral AI

    Magistral Small

    Released Jun 10, 2025

    49/100
    • ECI133.1
    • Price$0.50 / $1.50
    • Context131K
    Full specs Remove Magistral Small

  2. Alibaba (Qwen)

    Qwen3 30B A3B

    Released Apr 28, 2025

    57/100
    • ECI136.2
    • Price$0.108 / $0.475
    • Context131K
    Full specs Remove Qwen3 30B A3B

  3. OpenAI

    GPT-4.1 mini

    Released Apr 14, 2025

    59/100
    • ECI134.9
    • Price$0.40 / $1.60
    • Context1.05M
    Full specs Remove GPT-4.1 mini
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (GPT-4.1 mini 59/100, Qwen3 30B A3B 57/100, Magistral Small 49/100), so choose by what matters most for your work: Qwen3 30B A3B for raw capability and GPT-4.1 mini for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3 30B A3BCapabilities Index (ECI): Qwen3 30B A3B 136.2 · GPT-4.1 mini 134.9 · Magistral Small 133.1
  • Lowest priceQwen3 30B A3BQwen3 30B A3B $0.20 · GPT-4.1 mini $0.70 · Magistral Small $0.75 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · Magistral Small 131,072 · Qwen3 30B A3B 131,072 tokens
  • Widest inputsGPT-4.1 miniMagistral Small: Text · Qwen3 30B A3B: Text · GPT-4.1 mini: Text, Images, PDFs
  • Self-hostingMagistral Small and Qwen3 30B A3BPublishes downloadable weights (Apache 2.0)
How the score is built
MeasureWeightMagistral SmallQwen3 30B A3BGPT-4.1 mini
CapabilityCapabilities Index (ECI)50%565958
Price25%538055
Inputs & features15%353570
Context window10%252561
Overall100%49/10057/10059/100
02 — Side by side

Every spec in one table

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

Magistral Small vs Qwen3 30B A3B vs GPT-4.1 mini specifications side by side
SpecificationMagistral SmallMistral AIQwen3 30B A3BAlibaba (Qwen)GPT-4.1 miniOpenAI
Capability
Capabilities Index (ECI)133.1136.2 (best)134.9
ECI rank#134 of 165#126 of 165 (best)#129 of 165
GPQA DiamondGraduate-level science questions56.1%61.7%65.9% (best)
FrontierMath Tiers 1–3Research-level mathematics——6.7%
OTIS Mock AIME 2024–2025Competition mathematics30.0%62.8% (best)44.7%
SimpleQA VerifiedShort factual questions——12.7%
Price per million tokens
Input$0.50$0.108 (best)$0.40
Output$1.50$0.475 (best)$1.60
Cached input——$0.10
Blended (3:1)$0.75$0.20 (best)$0.70
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 14 providersOfficial OpenAI API
Limits
Context window131,072 tokens131,072 tokens1,047,576 tokens (best)
Max output8,192 tokens16,384 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenApache 2.0OpenProprietary
API model ID——gpt-4.1-mini
API providers21428 (best)
ReleasedJun 10, 2025Apr 28, 2025Apr 14, 2025
Knowledge cutoff——Apr 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.

  • Magistral Small$8.00
  • Qwen3 30B A3B$2.03
  • GPT-4.1 mini$7.20
04 — Questions

Which should you choose?

Which is better: Magistral Small, Qwen3 30B A3B or GPT-4.1 mini?

It is close. Our weighted score puts them within 2 points (GPT-4.1 mini 59/100, Qwen3 30B A3B 57/100, Magistral Small 49/100), so choose by what matters most for your work: Qwen3 30B A3B for raw capability and GPT-4.1 mini for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Magistral Small, Qwen3 30B A3B or GPT-4.1 mini?

Qwen3 30B A3B is cheaper at $0.108 input / $0.475 output per million tokens (median across 14 API providers). GPT-4.1 mini costs $0.40 input / $1.60 output per million tokens (official OpenAI API price); Magistral Small costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.20 per million tokens for Qwen3 30B A3B versus $0.70 for GPT-4.1 mini (3.5× as much) and $0.75 for Magistral Small (3.8× as much).

Which scores higher on benchmarks?

Qwen3 30B A3B scores higher on the Capabilities Index (ECI): Qwen3 30B A3B 136.2 (#126 of 165), GPT-4.1 mini 134.9 (#129 of 165) and Magistral Small 133.1 (#134 of 165). The confidence ranges of the top two overlap (130.8–138.5 vs 131.1–136.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-4.1 mini 65.9%, Qwen3 30B A3B 61.7%, Magistral Small 56.1%; OTIS Mock AIME 2024–2025 — Qwen3 30B A3B 62.8%, GPT-4.1 mini 44.7%, Magistral Small 30.0%.

Which is better for coding?

There are no published SWE-bench Verified results for Magistral Small, Qwen3 30B A3B and GPT-4.1 mini yet, so there is no like-for-like coding score. On overall capability, Qwen3 30B A3B 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?

GPT-4.1 mini has the largest context window at 1,047,576 tokens, against 131,072 for Magistral Small and 131,072 for Qwen3 30B A3B. Maximum output per response: Magistral Small up to 8,192, Qwen3 30B A3B up to 16,384, GPT-4.1 mini up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Magistral Small accepts text; Qwen3 30B A3B accepts text; GPT-4.1 mini accepts text, images and PDFs. GPT-4.1 mini handles the widest range of inputs.

Are any of these open source?

Magistral Small and Qwen3 30B A3B publishes its weights (Apache 2.0) and can be self-hosted; GPT-4.1 mini is proprietary.

Which is newer?

Magistral Small is the newest, released Jun 10, 2025. Qwen3 30B A3B came out Apr 28, 2025; GPT-4.1 mini came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 mini 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons