ZMIME
Comparison · 3 models · Updated Oct 4, 2026

DeepSeek-R1-Distill-Qwen-32B vs GPT OSS 20B vs Qwen3.5 9B

Qwen3.5 9B comes out ahead, 64 to 54 and 47 on our weighted score, and it is the cheaper option too.

  1. DeepSeek

    DeepSeek-R1-Distill-Qwen-32B

    Released Jan 20, 2025

    47/100
    • ECI137.4
    • Price—
    • Context131K
    Full specs Remove DeepSeek-R1-Distill-Qwen-32B

  2. OpenAI

    GPT OSS 20B

    Released Aug 5, 2025

    54/100
    • ECI137.8
    • Price$0.07 / $0.295
    • Context131K
    Full specs Remove GPT OSS 20B
  3. Our pick

    Alibaba (Qwen)

    Qwen3.5 9B

    Released Feb 23, 2026

    64/100
    • ECI139.5
    • Price$0.10 / $0.15
    • Context262K
    Full specs Remove Qwen3.5 9B
01 — Verdict

Qwen3.5 9B is our pick

Qwen3.5 9B is the better all-round choice, scoring 64/100 against GPT OSS 20B (54) and DeepSeek-R1-Distill-Qwen-32B (47). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityQwen3.5 9BCapabilities Index (ECI): Qwen3.5 9B 139.5 · GPT OSS 20B 137.8 · DeepSeek-R1-Distill-Qwen-32B 137.4
  • Lowest priceQwen3.5 9BQwen3.5 9B $0.113 · GPT OSS 20B $0.126 per 1M tokens (3:1 blend) · DeepSeek-R1-Distill-Qwen-32B unpriced
  • Longest contextQwen3.5 9BQwen3.5 9B 262,144 · DeepSeek-R1-Distill-Qwen-32B 131,072 · GPT OSS 20B 131,072 tokens
  • Widest inputsQwen3.5 9BDeepSeek-R1-Distill-Qwen-32B: Text · GPT OSS 20B: Text · Qwen3.5 9B: Text, Images, Video
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek-R1-Distill-Qwen-32BGPT OSS 20BQwen3.5 9B
CapabilityCapabilities Index (ECI)67%626365
Inputs & features20%104580
Context window13%242437
Overall100%47/10054/10064/100

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

02 — Side by side

Every spec in one table

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

DeepSeek-R1-Distill-Qwen-32B vs GPT OSS 20B vs Qwen3.5 9B specifications side by side
SpecificationDeepSeek-R1-Distill-Qwen-32BDeepSeekGPT OSS 20BOpenAIQwen3.5 9BAlibaba (Qwen)
Capability
Capabilities Index (ECI)137.4137.8139.5 (best)
ECI rank#110 of 148#108 of 148#101 of 148 (best)
GPQA DiamondGraduate-level science questions64.1%60.8%79.0% (best)
OTIS Mock AIME 2024–2025Competition mathematics55.6%65.3% (best)61.7%
Price per million tokens
Input—$0.07 (best)$0.10
Output—$0.295$0.15 (best)
Cached input———
Blended (3:1)—$0.126$0.113 (best)
Long-context rate—Same rateSame rate
Price source—Median of 18 providersMedian of 14 providers
Limits
Context window131,072 tokens131,072 tokens262,144 tokens (best)
Max output32,768 tokens32,768 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYes
Tool callingNoYesYes
Structured outputNoYesYes
Availability
WeightsOpenOpenOpen
API model ID———
API providers—19 (best)15
ReleasedJan 20, 2025Aug 5, 2025Feb 23, 2026
Knowledge cutoff———
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-Distill-Qwen-32B—
  • GPT OSS 20B$1.29
  • Qwen3.5 9B$1.30
04 — Questions

Which should you choose?

Which is better: DeepSeek-R1-Distill-Qwen-32B, GPT OSS 20B or Qwen3.5 9B?

Qwen3.5 9B is the better all-round choice, scoring 64/100 against GPT OSS 20B (54) and DeepSeek-R1-Distill-Qwen-32B (47). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek-R1-Distill-Qwen-32B, GPT OSS 20B or Qwen3.5 9B?

Qwen3.5 9B is cheaper at $0.10 input / $0.15 output per million tokens (median across 14 API providers). GPT OSS 20B costs $0.07 input / $0.295 output per million tokens (median across 18 API providers). At a typical mix of three input tokens to one output token, that is $0.113 per million tokens for Qwen3.5 9B versus $0.126 for GPT OSS 20B (1.1× as much). DeepSeek-R1-Distill-Qwen-32B has no published per-token price.

Which scores higher on benchmarks?

Qwen3.5 9B scores higher on the Capabilities Index (ECI): Qwen3.5 9B 139.5 (#101 of 148), GPT OSS 20B 137.8 (#108 of 148) and DeepSeek-R1-Distill-Qwen-32B 137.4 (#110 of 148). The confidence ranges of the top two overlap (136.5–141.3 vs 133.0–139.6), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen3.5 9B 79.0%, DeepSeek-R1-Distill-Qwen-32B 64.1%, GPT OSS 20B 60.8%; OTIS Mock AIME 2024–2025 — GPT OSS 20B 65.3%, Qwen3.5 9B 61.7%, DeepSeek-R1-Distill-Qwen-32B 55.6%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1-Distill-Qwen-32B, GPT OSS 20B and Qwen3.5 9B yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 9B leads, which tends to carry over to coding, but test on your own codebase. Note that DeepSeek-R1-Distill-Qwen-32B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen3.5 9B has the largest context window at 262,144 tokens, against 131,072 for DeepSeek-R1-Distill-Qwen-32B and 131,072 for GPT OSS 20B. Maximum output per response: DeepSeek-R1-Distill-Qwen-32B up to 32,768, GPT OSS 20B up to 32,768, Qwen3.5 9B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-R1-Distill-Qwen-32B accepts text; GPT OSS 20B accepts text; Qwen3.5 9B accepts text, images and video. Qwen3.5 9B handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

Qwen3.5 9B is the newest, released Feb 23, 2026. GPT OSS 20B came out Aug 5, 2025; DeepSeek-R1-Distill-Qwen-32B came out Jan 20, 2025.

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.

05 — Keep comparing

Related comparisons