ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GPT OSS 20B vs Mistral Small 3.2 vs Qwen3.5 9B

Qwen3.5 9B comes out ahead, 72 to 64 and 60 on our weighted score, and it is the cheaper option too.

  1. OpenAI

    GPT OSS 20B

    Released Aug 5, 2025

    64/100
    • ECI137.8
    • Price$0.07 / $0.295
    • Context131K
    Full specs Remove GPT OSS 20B

  2. Mistral AI

    Mistral Small 3.2

    Released Jun 20, 2025

    60/100
    • ECI131.7
    • Price$0.10 / $0.30
    • Context128K
    Full specs Remove Mistral Small 3.2
  3. Our pick

    Alibaba (Qwen)

    Qwen3.5 9B

    Released Feb 23, 2026

    72/100
    • 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 72/100 against GPT OSS 20B (64) and Mistral Small 3.2 (60). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3.5 9BCapabilities Index (ECI): Qwen3.5 9B 139.5 · GPT OSS 20B 137.8 · Mistral Small 3.2 131.7
  • Lowest priceQwen3.5 9BQwen3.5 9B $0.113 · GPT OSS 20B $0.126 · Mistral Small 3.2 $0.15 per 1M tokens (3:1 blend)
  • Longest contextQwen3.5 9BQwen3.5 9B 262,144 · GPT OSS 20B 131,072 · Mistral Small 3.2 128,000 tokens
  • Widest inputsQwen3.5 9BGPT OSS 20B: Text · Mistral Small 3.2: Text, Images · 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
MeasureWeightGPT OSS 20BMistral Small 3.2Qwen3.5 9B
CapabilityCapabilities Index (ECI)50%635565
Price25%928995
Inputs & features15%455080
Context window10%242437
Overall100%64/10060/10072/100
02 — Side by side

Every spec in one table

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

GPT OSS 20B vs Mistral Small 3.2 vs Qwen3.5 9B specifications side by side
SpecificationGPT OSS 20BOpenAIMistral Small 3.2Mistral AIQwen3.5 9BAlibaba (Qwen)
Capability
Capabilities Index (ECI)137.8131.7139.5 (best)
ECI rank#108 of 148#123 of 148#101 of 148 (best)
GPQA DiamondGraduate-level science questions60.8%49.1%79.0% (best)
OTIS Mock AIME 2024–2025Competition mathematics65.3% (best)30.3%61.7%
Price per million tokens
Input$0.07 (best)$0.10$0.10
Output$0.295$0.30$0.15 (best)
Cached input———
Blended (3:1)$0.126$0.15$0.113 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 18 providersOfficial Mistral APIMedian of 14 providers
Limits
Context window131,072 tokens128,000 tokens262,144 tokens (best)
Max output32,768 tokens16,384 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputYesNoYes
Availability
WeightsOpenOpenOpen
API model ID—mistral-small-2506—
API providers19 (best)615
ReleasedAug 5, 2025Jun 20, 2025Feb 23, 2026
Knowledge cutoff—Mar 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.

  • GPT OSS 20B$1.29
  • Mistral Small 3.2$1.60
  • Qwen3.5 9B$1.30
04 — Questions

Which should you choose?

Which is better: GPT OSS 20B, Mistral Small 3.2 or Qwen3.5 9B?

Qwen3.5 9B is the better all-round choice, scoring 72/100 against GPT OSS 20B (64) and Mistral Small 3.2 (60). It leads on capability, price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT OSS 20B, Mistral Small 3.2 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); Mistral Small 3.2 costs $0.10 input / $0.30 output per million tokens (official Mistral API price). 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) and $0.15 for Mistral Small 3.2 (1.3× as much).

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 Mistral Small 3.2 131.7 (#123 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%, GPT OSS 20B 60.8%, Mistral Small 3.2 49.1%; OTIS Mock AIME 2024–2025 — GPT OSS 20B 65.3%, Qwen3.5 9B 61.7%, Mistral Small 3.2 30.3%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT OSS 20B, Mistral Small 3.2 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. All three support tool calling for agent workflows.

Which has the bigger context window?

Qwen3.5 9B has the largest context window at 262,144 tokens, against 131,072 for GPT OSS 20B and 128,000 for Mistral Small 3.2. Maximum output per response: GPT OSS 20B up to 32,768, Mistral Small 3.2 up to 16,384, Qwen3.5 9B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT OSS 20B accepts text; Mistral Small 3.2 accepts text and images; 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; Mistral Small 3.2 came out Jun 20, 2025. Knowledge cutoff: Mistral Small 3.2 Mar 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