ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen3 30B A3B vs DeepSeek-R1 vs Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite comes out ahead, 71 to 58 and 51 on our weighted score, and it is the cheaper option too.

  1. 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

  2. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    51/100
    • ECI139.0
    • Price$0.70 / $2.60
    • Context128K
    Full specs Remove DeepSeek-R1
  3. Our pick

    Google

    Gemini 2.5 Flash-Lite

    Released Jun 17, 2025

    71/100
    • ECI133.9
    • Price$0.10 / $0.40
    • Context1.05M
    Full specs Remove Gemini 2.5 Flash-Lite
01 — Verdict

Gemini 2.5 Flash-Lite is our pick

Gemini 2.5 Flash-Lite is the better all-round choice, scoring 71/100 against Qwen3 30B A3B (58) and DeepSeek-R1 (51). It leads on price, inputs & features and context window. DeepSeek-R1 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek-R1Capabilities Index (ECI): DeepSeek-R1 139.0 · Qwen3 30B A3B 136.2 · Gemini 2.5 Flash-Lite 133.9
  • Lowest priceGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite $0.175 · Qwen3 30B A3B $0.21 · DeepSeek-R1 $1.18 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Qwen3 30B A3B 131,072 · DeepSeek-R1 128,000 tokens
  • Widest inputsGemini 2.5 Flash-LiteQwen3 30B A3B: Text · DeepSeek-R1: Text · Gemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video
  • Self-hostingQwen3 30B A3B and DeepSeek-R1Publishes downloadable weights
How the score is built
MeasureWeightQwen3 30B A3BDeepSeek-R1Gemini 2.5 Flash-Lite
CapabilityCapabilities Index (ECI)50%616458
Price25%824786
Inputs & features15%3535100
Context window10%242461
Overall100%58/10051/10071/100
02 — Side by side

Every spec in one table

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

Qwen3 30B A3B vs DeepSeek-R1 vs Gemini 2.5 Flash-Lite specifications side by side
SpecificationQwen3 30B A3BAlibaba (Qwen)DeepSeek-R1DeepSeekGemini 2.5 Flash-LiteGoogle
Capability
Capabilities Index (ECI)136.2139.0 (best)133.9
ECI rank#112 of 148#104 of 148 (best)#118 of 148
GPQA DiamondGraduate-level science questions61.7%71.7% (best)—
OTIS Mock AIME 2024–2025Competition mathematics62.8% (best)53.3%—
Price per million tokens
Input$0.114$0.70$0.10 (best)
Output$0.50$2.60$0.40 (best)
Cached input——$0.01
Blended (3:1)$0.21$1.18$0.175 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 8 providersMedian of 11 providersOfficial Google API
Limits
Context window131,072 tokens128,000 tokens1,048,576 tokens (best)
Max output16,384 tokens32,768 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoYes
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenOpenProprietary
API model ID——gemini-2.5-flash-lite
API providers81220 (best)
ReleasedApr 28, 2025Jan 20, 2025Jun 17, 2025
Knowledge cutoff—Jul 2024Jan 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.

  • Qwen3 30B A3B$2.14
  • DeepSeek-R1$12.20
  • Gemini 2.5 Flash-Lite$1.80
04 — Questions

Which should you choose?

Which is better: Qwen3 30B A3B, DeepSeek-R1 or Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is the better all-round choice, scoring 71/100 against Qwen3 30B A3B (58) and DeepSeek-R1 (51). It leads on price, inputs & features and context window. DeepSeek-R1 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Qwen3 30B A3B, DeepSeek-R1 or Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is cheaper at $0.10 input / $0.40 output per million tokens (official Google API price). Qwen3 30B A3B costs $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). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for Gemini 2.5 Flash-Lite versus $0.21 for Qwen3 30B A3B (1.2× as much) and $1.18 for DeepSeek-R1 (6.7× as much).

Which scores higher on benchmarks?

DeepSeek-R1 scores higher on the Capabilities Index (ECI): DeepSeek-R1 139.0 (#104 of 148), Qwen3 30B A3B 136.2 (#112 of 148) and Gemini 2.5 Flash-Lite 133.9 (#118 of 148). The confidence ranges of the top two overlap (136.2–140.4 vs 130.3–138.7), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen3 30B A3B, DeepSeek-R1 and Gemini 2.5 Flash-Lite 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 2.5 Flash-Lite 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: Qwen3 30B A3B up to 16,384, DeepSeek-R1 up to 32,768, Gemini 2.5 Flash-Lite up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Qwen3 30B A3B accepts text; DeepSeek-R1 accepts text; Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video. Gemini 2.5 Flash-Lite handles the widest range of inputs.

Are any of these open source?

Qwen3 30B A3B and DeepSeek-R1 publishes its weights and can be self-hosted; Gemini 2.5 Flash-Lite is proprietary.

Which is newer?

Gemini 2.5 Flash-Lite is the newest, released Jun 17, 2025. Qwen3 30B A3B came out Apr 28, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Gemini 2.5 Flash-Lite Jan 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