ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek-R1 vs Gemini 2.0 Flash vs Qwen3 30B A3B

Gemini 2.0 Flash comes out ahead, 66 to 56 and 53 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    56/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
  2. Our pick

    Google

    Gemini 2.0 Flash

    Released Dec 11, 2024

    66/100
    • ECI134.0
    • Price$0.10 / $0.42
    • Context1.05M
  3. Alibaba (Qwen)

    Qwen3 30B A3B

    Released Apr 28, 2025

    53/100
    • ECI134.2
    • Price$0.109 / $0.50
    • Context131K
01 — Verdict

Gemini 2.0 Flash is our pick

Gemini 2.0 Flash is the better all-round choice, scoring 66/100 against DeepSeek-R1 (56) and Qwen3 30B A3B (53). It leads on inputs & features and context window. DeepSeek-R1 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityDeepSeek-R1Capabilities Index (ECI): DeepSeek-R1 138.6 · Qwen3 30B A3B 134.2 · Gemini 2.0 Flash 134.0
  • Lowest priceGemini 2.0 FlashGemini 2.0 Flash $0.18 · Qwen3 30B A3B $0.206 · DeepSeek-R1 $2.05 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.0 FlashGemini 2.0 Flash 1,048,576 · Qwen3 30B A3B 131,072 · DeepSeek-R1 128,000 tokens
  • Widest inputsGemini 2.0 FlashDeepSeek-R1: Text · Gemini 2.0 Flash: Text, Images, PDFs, Audio, Video · Qwen3 30B A3B: Text
  • Self-hostingDeepSeek-R1 and Qwen3 30B A3BPublishes downloadable weights
How the score is built
MeasureWeightDeepSeek-R1Gemini 2.0 FlashQwen3 30B A3B
CapabilityCapabilities Index (ECI)67%676262
Inputs & features20%358035
Context window13%326532
Overall100%56/10066/10053/100
02 — Side by side

Every spec in one table

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

DeepSeek-R1 vs Gemini 2.0 Flash vs Qwen3 30B A3B specifications side by side
SpecificationDeepSeek-R1DeepSeekGemini 2.0 FlashGoogleQwen3 30B A3BAlibaba (Qwen)
Capability
Capabilities Index (ECI)138.6 (best)134.0134.2
ECI rank#118 of 158 (best)#130 of 158#129 of 158
GPQA DiamondGraduate-level science questions71.7% (best)64.1%61.7%
OTIS Mock AIME 2024–2025Competition mathematics53.3%31.1%62.8% (best)
Price per million tokens
Input$1.02$0.10 (best)$0.109
Output$5.14$0.42 (best)$0.50
Cached input———
Blended (3:1)$2.05$0.18 (best)$0.206
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 12 providersMedian of 1 providersMedian of 15 providers
Limits
Context window128,000 tokens1,048,576 tokens (best)131,072 tokens
Max output32,768 tokens (best)8,192 tokens16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoYesNo
VideoNoYesNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpen
API model ID———
API providers13215 (best)
ReleasedJan 20, 2025Dec 11, 2024Apr 28, 2025
Knowledge cutoffJul 2024Jun 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.

  • DeepSeek-R1$20.53
  • Gemini 2.0 Flash$1.84
  • Qwen3 30B A3B$2.09
04 — Questions

Which should you choose?

Which is better: DeepSeek-R1, Gemini 2.0 Flash or Qwen3 30B A3B?

Gemini 2.0 Flash is the better all-round choice, scoring 66/100 against DeepSeek-R1 (56) and Qwen3 30B A3B (53). It leads on inputs & features and context window. DeepSeek-R1 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek-R1, Gemini 2.0 Flash or Qwen3 30B A3B?

Gemini 2.0 Flash is cheaper at $0.10 input / $0.42 output per million tokens (median across 1 API provider). Qwen3 30B A3B costs $0.109 input / $0.50 output per million tokens (median across 15 API providers); DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers). At a typical mix of three input tokens to one output token, that is $0.18 per million tokens for Gemini 2.0 Flash versus $0.206 for Qwen3 30B A3B (1.1× as much) and $2.05 for DeepSeek-R1 (11× as much).

Which scores higher on benchmarks?

DeepSeek-R1 scores higher on the Capabilities Index (ECI): DeepSeek-R1 138.6 (#118 of 158), Qwen3 30B A3B 134.2 (#129 of 158) and Gemini 2.0 Flash 134.0 (#130 of 158). The confidence ranges of the top two overlap (136.7–140.4 vs 131.5–136.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek-R1 71.7%, Gemini 2.0 Flash 64.1%, Qwen3 30B A3B 61.7%; OTIS Mock AIME 2024–2025 — Qwen3 30B A3B 62.8%, DeepSeek-R1 53.3%, Gemini 2.0 Flash 31.1%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1, Gemini 2.0 Flash and Qwen3 30B A3B yet, so there is no like-for-like coding score. On overall capability, DeepSeek-R1 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?

Gemini 2.0 Flash has the largest context window at 1,048,576 tokens, against 131,072 for Qwen3 30B A3B and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, Gemini 2.0 Flash up to 8,192, Qwen3 30B A3B up to 16,384 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-R1 accepts text; Gemini 2.0 Flash accepts text, images, PDFs, audio and video; Qwen3 30B A3B accepts text. Gemini 2.0 Flash handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 and Qwen3 30B A3B publishes its weights and can be self-hosted; Gemini 2.0 Flash is proprietary.

Which is newer?

Qwen3 30B A3B is the newest, released Apr 28, 2025. DeepSeek-R1 came out Jan 20, 2025; Gemini 2.0 Flash came out Dec 11, 2024. Knowledge cutoff: DeepSeek-R1 Jul 2024, Gemini 2.0 Flash Jun 2024.

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.