ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3 235B-A22B vs Qwen3 30B A3B vs DeepSeek-R1

Qwen3 30B A3B comes out ahead, 58 to 51 and 51 on our weighted score, and it is the cheaper option too.

  1. Alibaba (Qwen)

    Qwen3 235B-A22B

    Released Apr 28, 2025

    51/100
    • ECI139.4
    • Price$0.70 / $2.80
    • Context131K
    Full specs Remove Qwen3 235B-A22B
  2. Our pick

    Alibaba (Qwen)

    Qwen3 30B A3B

    Released Apr 28, 2025

    58/100
    • ECI136.2
    • Price$0.114 / $0.50
    • Context131K
    Full specs Remove Qwen3 30B A3B

  3. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    51/100
    • ECI139.0
    • Price$0.70 / $2.60
    • Context128K
    Full specs Remove DeepSeek-R1
01 — Verdict

Qwen3 30B A3B is our pick

Qwen3 30B A3B is the better all-round choice, scoring 58/100 against Qwen3 235B-A22B (51) and DeepSeek-R1 (51). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityQwen3 235B-A22BCapabilities Index (ECI): Qwen3 235B-A22B 139.4 · DeepSeek-R1 139.0 · Qwen3 30B A3B 136.2
  • Lowest priceQwen3 30B A3BQwen3 30B A3B $0.21 · DeepSeek-R1 $1.18 · Qwen3 235B-A22B $1.23 per 1M tokens (3:1 blend)
  • Longest contextQwen3 235B-A22B and Qwen3 30B A3BQwen3 235B-A22B 131,072 · Qwen3 30B A3B 131,072 · DeepSeek-R1 128,000 tokens
  • Widest inputsSame inputsQwen3 235B-A22B: Text · Qwen3 30B A3B: Text · DeepSeek-R1: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightQwen3 235B-A22BQwen3 30B A3BDeepSeek-R1
CapabilityCapabilities Index (ECI)50%656164
Price25%468247
Inputs & features15%353535
Context window10%242424
Overall100%51/10058/10051/100
02 — Side by side

Every spec in one table

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

Qwen3 235B-A22B vs Qwen3 30B A3B vs DeepSeek-R1 specifications side by side
SpecificationQwen3 235B-A22BAlibaba (Qwen)Qwen3 30B A3BAlibaba (Qwen)DeepSeek-R1DeepSeek
Capability
Capabilities Index (ECI)139.4 (best)136.2139.0
ECI rank#103 of 148 (best)#112 of 148#104 of 148
GPQA DiamondGraduate-level science questions70.7%61.7%71.7% (best)
OTIS Mock AIME 2024–2025Competition mathematics—62.8% (best)53.3%
Price per million tokens
Input$0.70$0.114 (best)$0.70
Output$2.80$0.50 (best)$2.60
Cached input———
Blended (3:1)$1.23$0.21 (best)$1.18
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIMedian of 8 providersMedian of 11 providers
Limits
Context window131,072 tokens (best)131,072 tokens (best)128,000 tokens
Max output16,384 tokens16,384 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model IDqwen3-235b-a22b——
API providers7812 (best)
ReleasedApr 28, 2025Apr 28, 2025Jan 20, 2025
Knowledge cutoffApr 2025—Jul 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.

  • Qwen3 235B-A22B$12.60
  • Qwen3 30B A3B$2.14
  • DeepSeek-R1$12.20
04 — Questions

Which should you choose?

Which is better: Qwen3 235B-A22B, Qwen3 30B A3B or DeepSeek-R1?

Qwen3 30B A3B is the better all-round choice, scoring 58/100 against Qwen3 235B-A22B (51) and DeepSeek-R1 (51). It leads on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3 235B-A22B, Qwen3 30B A3B or DeepSeek-R1?

Qwen3 30B A3B is cheaper at $0.114 input / $0.50 output per million tokens (median across 8 API providers). DeepSeek-R1 costs $0.70 input / $2.60 output per million tokens (median across 11 API providers); Qwen3 235B-A22B 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 $0.21 per million tokens for Qwen3 30B A3B versus $1.18 for DeepSeek-R1 (5.6× as much) and $1.23 for Qwen3 235B-A22B (5.8× as much).

Which scores higher on benchmarks?

Qwen3 235B-A22B scores higher on the Capabilities Index (ECI): Qwen3 235B-A22B 139.4 (#103 of 148), DeepSeek-R1 139.0 (#104 of 148) and Qwen3 30B A3B 136.2 (#112 of 148). The confidence ranges of the top two overlap (135.2–140.8 vs 136.2–140.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek-R1 71.7%, Qwen3 235B-A22B 70.7%, Qwen3 30B A3B 61.7%.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 235B-A22B, Qwen3 30B A3B and DeepSeek-R1 yet, so there is no like-for-like coding score. On overall capability, Qwen3 235B-A22B 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 235B-A22B and Qwen3 30B A3B have the largest context windows (131,072 and 131,072 tokens), against 128,000 for DeepSeek-R1. Maximum output per response: Qwen3 235B-A22B up to 16,384, Qwen3 30B A3B up to 16,384, DeepSeek-R1 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Qwen3 235B-A22B accepts text; Qwen3 30B A3B accepts text; DeepSeek-R1 accepts text. They handle the same number of input types.

Are any of these open source?

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

Which is newer?

Qwen3 235B-A22B is the newest, released Apr 28, 2025. Qwen3 30B A3B came out Apr 28, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: Qwen3 235B-A22B Apr 2025, DeepSeek-R1 Jul 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons