ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek R1 0528 vs GPT-4.1 mini vs Qwen3 32B

GPT-4.1 mini comes out ahead, 64 to 57 and 55 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    57/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  2. Our pick

    OpenAI

    GPT-4.1 mini

    Released Apr 14, 2025

    64/100
    • ECI134.3
    • Price$0.40 / $1.60
    • Context1.05M
  3. Alibaba (Qwen)

    Qwen3 32B

    Released Apr 28, 2025Deprecated

    55/100
    • ECI136.8
    • Price$0.70 / $2.80
    • Context131K
01 — Verdict

GPT-4.1 mini is our pick

GPT-4.1 mini is the better all-round choice, scoring 64/100 against DeepSeek R1 0528 (57) and Qwen3 32B (55). It leads on inputs & features and context window. DeepSeek R1 0528 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityDeepSeek R1 0528Capabilities Index (ECI): DeepSeek R1 0528 140.8 · Qwen3 32B 136.8 · GPT-4.1 mini 134.3
  • Lowest priceGPT-4.1 miniGPT-4.1 mini $0.70 · DeepSeek R1 0528 $0.932 · Qwen3 32B $1.23 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · DeepSeek R1 0528 163,840 · Qwen3 32B 131,072 tokens
  • Widest inputsGPT-4.1 miniDeepSeek R1 0528: Text · GPT-4.1 mini: Text, Images, PDFs · Qwen3 32B: Text
  • Self-hostingDeepSeek R1 0528 and Qwen3 32BPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek R1 0528GPT-4.1 miniQwen3 32B
CapabilityCapabilities Index (ECI)67%696265
Inputs & features20%357035
Context window13%366532
Overall100%57/10064/10055/100
02 — Side by side

Every spec in one table

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

DeepSeek R1 0528 vs GPT-4.1 mini vs Qwen3 32B specifications side by side
SpecificationDeepSeek R1 0528DeepSeekGPT-4.1 miniOpenAIQwen3 32BAlibaba (Qwen)
Capability
Capabilities Index (ECI)140.8 (best)134.3136.8
ECI rank#113 of 158 (best)#128 of 158#121 of 158
GPQA DiamondGraduate-level science questions76.3% (best)65.9%65.7%
FrontierMath Tiers 1–3Research-level mathematics—6.7%—
OTIS Mock AIME 2024–2025Competition mathematics66.4%44.7%66.9% (best)
SimpleQA VerifiedShort factual questions—12.7%—
Price per million tokens
Input$0.512$0.40 (best)$0.70
Output$2.19$1.60 (best)$2.80
Cached input—$0.10—
Blended (3:1)$0.932$0.70 (best)$1.23
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 16 providersOfficial OpenAI APIOfficial Alibaba API
Limits
Context window163,840 tokens1,047,576 tokens (best)131,072 tokens
Max output32,768 tokens (best)32,768 tokens (best)16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenMITProprietaryOpen
API model ID—gpt-4.1-miniqwen3-32b
API providers1630 (best)19
ReleasedMay 28, 2025Apr 14, 2025Apr 28, 2025
Knowledge cutoff—Apr 2024Apr 2025
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.

  • DeepSeek R1 0528$9.50
  • GPT-4.1 mini$7.20
  • Qwen3 32B$12.60
04 — Questions

Which should you choose?

Which is better: DeepSeek R1 0528, GPT-4.1 mini or Qwen3 32B?

GPT-4.1 mini is the better all-round choice, scoring 64/100 against DeepSeek R1 0528 (57) and Qwen3 32B (55). It leads on inputs & features and context window. DeepSeek R1 0528 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek R1 0528, GPT-4.1 mini or Qwen3 32B?

GPT-4.1 mini is cheaper at $0.40 input / $1.60 output per million tokens (official OpenAI API price). DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers); Qwen3 32B 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 $0.70 per million tokens for GPT-4.1 mini versus $0.932 for DeepSeek R1 0528 (1.3× as much) and $1.23 for Qwen3 32B (1.8× as much).

Which scores higher on benchmarks?

DeepSeek R1 0528 scores higher on the Capabilities Index (ECI): DeepSeek R1 0528 140.8 (#113 of 158), Qwen3 32B 136.8 (#121 of 158) and GPT-4.1 mini 134.3 (#128 of 158). The confidence ranges of the top two overlap (138.9–142.5 vs 134.4–139.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, GPT-4.1 mini 65.9%, Qwen3 32B 65.7%; OTIS Mock AIME 2024–2025 — Qwen3 32B 66.9%, DeepSeek R1 0528 66.4%, GPT-4.1 mini 44.7%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek R1 0528, GPT-4.1 mini and Qwen3 32B yet, so there is no like-for-like coding score. On overall capability, DeepSeek R1 0528 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 163,840 for DeepSeek R1 0528 and 131,072 for Qwen3 32B. Maximum output per response: DeepSeek R1 0528 up to 32,768, GPT-4.1 mini up to 32,768, Qwen3 32B up to 16,384 tokens.

Which can read images, PDFs, audio or video?

DeepSeek R1 0528 accepts text; GPT-4.1 mini accepts text, images and PDFs; Qwen3 32B accepts text. GPT-4.1 mini handles the widest range of inputs.

Are any of these open source?

DeepSeek R1 0528 and Qwen3 32B publishes its weights (MIT) and can be self-hosted; GPT-4.1 mini is proprietary.

Which is newer?

DeepSeek R1 0528 is the newest, released May 28, 2025. Qwen3 32B came out Apr 28, 2025; GPT-4.1 mini came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 mini Apr 2024, Qwen3 32B Apr 2025.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 18, 2026.