ZMIME
Comparison · 3 models · Updated Nov 22, 2026

DeepSeek R1 0528 vs GPT-4.1 vs Qwen3 32B

DeepSeek R1 0528 comes out ahead, 59 to 55 and 52 on our weighted score, and it is the cheaper option too.Too close to call on our weighted score (GPT-4.1 65, DeepSeek R1 0528 63, Qwen3 32B 60). The right pick depends on what you value most.

  1. Our pick

    DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    59/100
    • ECI140.7
    • Price$0.571 / $2.29
    • Context164K
  2. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    52/100
    • ECI136.1
    • Price$2.00 / $8.00
    • Context1.05M
  3. Alibaba (Qwen)

    Qwen3 32B

    Released Apr 28, 2025Deprecated

    55/100
    • ECI136.9
    • Price$0.70 / $2.80
    • Context131K
  4. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    63/100
    • ECI140.7
    • Price$0.571 / $2.29
    • Context164K
  5. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    65/100
    • ECI136.1
    • Price$2.00 / $8.00
    • Context1.05M
  6. Alibaba (Qwen)

    Qwen3 32B

    Released Apr 28, 2025Deprecated

    60/100
    • ECI136.9
    • Price$0.70 / $2.80
    • Context131K
01 — Verdict

DeepSeek R1 0528 is our pickToo close to call

DeepSeek R1 0528 is the better all-round choice, scoring 59/100 against Qwen3 32B (55) and GPT-4.1 (52). It leads on capability and price. GPT-4.1 wins on context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (GPT-4.1 65/100, DeepSeek R1 0528 63/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability and GPT-4.1 for long inputs. The score weighs capability 83%, context window 17%.

  • CapabilityDeepSeek R1 0528Capabilities Index (ECI): DeepSeek R1 0528 140.7 · Qwen3 32B 136.9 · GPT-4.1 136.1
  • Lowest priceDeepSeek R1 0528DeepSeek R1 0528 $1 · Qwen3 32B $1.23 · GPT-4.1 $3.50 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · DeepSeek R1 0528 163,840 · Qwen3 32B 131,072 tokens
  • Widest inputsGPT-4.1DeepSeek R1 0528: Text · GPT-4.1: Text, Images, PDFs · Qwen3 32B: Text
  • Self-hostingDeepSeek R1 0528 and Qwen3 32BPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek R1 0528GPT-4.1Qwen3 32B
CapabilityCapabilities Index (ECI)59%696565
Price29%482344
Context window12%366532
Overall100%59/10052/10055/100

Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightDeepSeek R1 0528GPT-4.1Qwen3 32B
CapabilityCapabilities Index (ECI)83%696565
Context window17%366532
Overall100%63/10065/10060/100

Left out because at least one model lacks the data: inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

DeepSeek R1 0528 vs GPT-4.1 vs Qwen3 32B specifications side by side
SpecificationDeepSeek R1 0528DeepSeekGPT-4.1OpenAIQwen3 32BAlibaba (Qwen)
Capability
Capabilities Index (ECI)140.7 (best)136.1136.9
ECI rank#114 of 159 (best)#124 of 159#122 of 159
ECI confidence interval138.9–142.4134.2–138.0134.4–139.1
ECI evaluation dateMay 28, 2025Apr 14, 2025Apr 29, 2025
Documented capabilitiesMay 2025 DeepSeek R1 update with improved mathematics, coding, and reasoningLong-lived GPT workhorse for coding, instruction following, and production appsDense open Qwen model for self-hosted chat, reasoning, and coding
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
GPQA DiamondGraduate-level science questions76.3% (best)66.9%65.7%
FrontierMath Tiers 1–3Research-level mathematicsNot published6.0%Not published
OTIS Mock AIME 2024–2025Competition mathematics66.4%38.3%66.9% (best)
SWE-bench VerifiedFixing real GitHub issuesNot published48.5%Not published
SimpleQA VerifiedShort factual questionsNot published31.1%Not published
Publisher-reported benchmarks
Aider PolyglotPublisher-reported resultNot published52.4percent correctReported resultApr 14, 202540percent correctReported resultMay 8, 2025
Price per million tokens
Input$0.571 (best)$2.00$0.70
Output$2.29 (best)$8.00$2.80
Cached inputNot published$0.50Not published
Blended (3:1)$1 (best)$3.50$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 inputNot publishedNot publishedNot published
Max output32,768 tokens (best)32,768 tokens (best)16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNot publishedYesNot published
File attachmentsNoYesNo
Temperature controlYesYesYes
Reasoning controlalwaysNot publishedbudget
Availability
WeightsOpenMITProprietaryOpen
API model IDNot publishedgpt-4.1qwen3-32b
API providers1632 (best)19
ReleasedMay 28, 2025Apr 14, 2025Apr 28, 2025
Knowledge cutoffNot publishedApr 2024Apr 2025
Publisher documentationModel weightsPublisher documentationPublisher documentation · Model weights
Source metadata updatedMay 28, 2025Apr 14, 2025Apr 28, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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$10.28
  • GPT-4.1$36.00
  • Qwen3 32B$12.60
04 — Questions

Which should you choose?

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

DeepSeek R1 0528 is the better all-round choice, scoring 59/100 against Qwen3 32B (55) and GPT-4.1 (52). It leads on capability and price. GPT-4.1 wins on context window. The score weighs capability 59%, price 29%, context window 12%.It is close. Our weighted score puts them within 1 points (GPT-4.1 65/100, DeepSeek R1 0528 63/100, Qwen3 32B 60/100), so choose by what matters most for your work: DeepSeek R1 0528 for raw capability and GPT-4.1 for long inputs. The score weighs capability 83%, context window 17%.

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

DeepSeek R1 0528 is cheaper at $0.571 input / $2.29 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); GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $1 per million tokens for DeepSeek R1 0528 versus $1.23 for Qwen3 32B (1.2× as much) and $3.50 for GPT-4.1 (3.5× as much).

Which scores higher on benchmarks?

DeepSeek R1 0528 scores higher on the Capabilities Index (ECI): DeepSeek R1 0528 140.7 (#114 of 159), Qwen3 32B 136.9 (#122 of 159) and GPT-4.1 136.1 (#124 of 159). The confidence ranges of the top two overlap (138.9–142.4 vs 134.4–139.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, GPT-4.1 66.9%, Qwen3 32B 65.7%; OTIS Mock AIME 2024–2025 — Qwen3 32B 66.9%, DeepSeek R1 0528 66.4%, GPT-4.1 38.3%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek R1 0528 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 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 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 accepts text, images and PDFs; Qwen3 32B accepts text. GPT-4.1 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 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 came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 Apr 2024, Qwen3 32B Apr 2025.

How do you decide the winner?

This rating uses capability (59%, independent benchmark results); price (29%, blended price per million tokens (3 input : 1 output), log scale); context window (12%, 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 22, 2026.This rating uses capability (83%, independent benchmark results); context window (17%, 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 22, 2026.