ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Gemini 2.5 Flash Preview 05-20 vs GPT-5 Mini vs Qwen3 235B-A22B Thinking 2507

Too close to call on our weighted score (Gemini 2.5 Flash Preview 05-20 67, GPT-5 Mini 64, Qwen3 235B-A22B Thinking 2507 55). The right pick depends on what you value most.

  1. Google

    Gemini 2.5 Flash Preview 05-20

    Released May 20, 2025

    67/100
    • ECI141.5
    • Price$0.146 / $1.96
    • Context1.05M
    Full specs Remove Gemini 2.5 Flash Preview 05-20

  2. OpenAI

    GPT-5 Mini

    Released Aug 7, 2025

    64/100
    • ECI145.4
    • Price$0.25 / $2.00
    • Context400K
    Full specs Remove GPT-5 Mini

  3. Alibaba (Qwen)

    Qwen3 235B-A22B Thinking 2507

    Released Jul 25, 2025

    55/100
    • ECI143.8
    • Price$0.30 / $2.90
    • Context262K
    Full specs Remove Qwen3 235B-A22B Thinking 2507
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 3 points (Gemini 2.5 Flash Preview 05-20 67/100, GPT-5 Mini 64/100, Qwen3 235B-A22B Thinking 2507 55/100), so choose by what matters most for your work: GPT-5 Mini for raw capability, Gemini 2.5 Flash Preview 05-20 on price and Gemini 2.5 Flash Preview 05-20 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-5 MiniCapabilities Index (ECI): GPT-5 Mini 145.4 · Qwen3 235B-A22B Thinking 2507 143.8 · Gemini 2.5 Flash Preview 05-20 141.5
  • Lowest priceGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 $0.60 · GPT-5 Mini $0.688 · Qwen3 235B-A22B Thinking 2507 $0.95 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 1,048,576 · GPT-5 Mini 400,000 · Qwen3 235B-A22B Thinking 2507 262,144 tokens
  • Widest inputsGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20: Text, Images, PDFs, Audio, Video · GPT-5 Mini: Text, Images · Qwen3 235B-A22B Thinking 2507: Text
  • Self-hostingQwen3 235B-A22B Thinking 2507Publishes downloadable weights (Apache 2.0)
How the score is built
MeasureWeightGemini 2.5 Flash Preview 05-20GPT-5 MiniQwen3 235B-A22B Thinking 2507
CapabilityCapabilities Index (ECI)50%667169
Price25%585549
Inputs & features15%907035
Context window10%614437
Overall100%67/10064/10055/100
02 — Side by side

Every spec in one table

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

Gemini 2.5 Flash Preview 05-20 vs GPT-5 Mini vs Qwen3 235B-A22B Thinking 2507 specifications side by side
SpecificationGemini 2.5 Flash Preview 05-20GoogleGPT-5 MiniOpenAIQwen3 235B-A22B Thinking 2507Alibaba (Qwen)
Capability
Capabilities Index (ECI)141.5145.4 (best)143.8
ECI rank#106 of 165#87 of 165 (best)#93 of 165
GPQA DiamondGraduate-level science questions—75.0%80.1% (best)
FrontierMath Tiers 1–3Research-level mathematics—46.7%—
OTIS Mock AIME 2024–2025Competition mathematics70.8%86.7% (best)86.7% (best)
SWE-bench VerifiedFixing real GitHub issues—64.7%—
SimpleQA VerifiedShort factual questions—21.6%40.4% (best)
Price per million tokens
Input$0.146 (best)$0.25$0.30
Output$1.96 (best)$2.00$2.90
Cached input—$0.025—
Blended (3:1)$0.60 (best)$0.688$0.95
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 2 providersOfficial OpenAI APIMedian of 11 providers
Limits
Context window1,048,576 tokens (best)400,000 tokens262,144 tokens
Max output65,536 tokens128,000 tokens (best)81,920 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesYesminimal · low · medium · highYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryOpenApache 2.0
API model ID—gpt-5-mini—
API providers235 (best)12
ReleasedMay 20, 2025Aug 7, 2025Jul 25, 2025
Knowledge cutoffJan 2025May 30, 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.

  • Gemini 2.5 Flash Preview 05-20$5.39
  • GPT-5 Mini$6.50
  • Qwen3 235B-A22B Thinking 2507$8.80
04 — Questions

Which should you choose?

Which is better: Gemini 2.5 Flash Preview 05-20, GPT-5 Mini or Qwen3 235B-A22B Thinking 2507?

It is close. Our weighted score puts them within 3 points (Gemini 2.5 Flash Preview 05-20 67/100, GPT-5 Mini 64/100, Qwen3 235B-A22B Thinking 2507 55/100), so choose by what matters most for your work: GPT-5 Mini for raw capability, Gemini 2.5 Flash Preview 05-20 on price and Gemini 2.5 Flash Preview 05-20 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemini 2.5 Flash Preview 05-20, GPT-5 Mini or Qwen3 235B-A22B Thinking 2507?

Gemini 2.5 Flash Preview 05-20 is cheaper at $0.146 input / $1.96 output per million tokens (median across 2 API providers). GPT-5 Mini costs $0.25 input / $2.00 output per million tokens (official OpenAI API price); Qwen3 235B-A22B Thinking 2507 costs $0.30 input / $2.90 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.60 per million tokens for Gemini 2.5 Flash Preview 05-20 versus $0.688 for GPT-5 Mini (1.1× as much) and $0.95 for Qwen3 235B-A22B Thinking 2507 (1.6× as much).

Which scores higher on benchmarks?

GPT-5 Mini scores higher on the Capabilities Index (ECI): GPT-5 Mini 145.4 (#87 of 165), Qwen3 235B-A22B Thinking 2507 143.8 (#93 of 165) and Gemini 2.5 Flash Preview 05-20 141.5 (#106 of 165). The confidence ranges of the top two overlap (143.5–147.1 vs 141.9–145.2), so treat the gap as small. On individual benchmarks: OTIS Mock AIME 2024–2025 — GPT-5 Mini 86.7%, Qwen3 235B-A22B Thinking 2507 86.7%, Gemini 2.5 Flash Preview 05-20 70.8%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 2.5 Flash Preview 05-20 and Qwen3 235B-A22B Thinking 2507 yet, so there is no like-for-like coding score. On overall capability, GPT-5 Mini 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 Preview 05-20 has the largest context window at 1,048,576 tokens, against 400,000 for GPT-5 Mini and 262,144 for Qwen3 235B-A22B Thinking 2507. Maximum output per response: Gemini 2.5 Flash Preview 05-20 up to 65,536, GPT-5 Mini up to 128,000, Qwen3 235B-A22B Thinking 2507 up to 81,920 tokens.

Which can read images, PDFs, audio or video?

Gemini 2.5 Flash Preview 05-20 accepts text, images, PDFs, audio and video; GPT-5 Mini accepts text and images; Qwen3 235B-A22B Thinking 2507 accepts text. Gemini 2.5 Flash Preview 05-20 handles the widest range of inputs.

Are any of these open source?

Qwen3 235B-A22B Thinking 2507 publishes its weights (Apache 2.0) and can be self-hosted; Gemini 2.5 Flash Preview 05-20 and GPT-5 Mini is proprietary.

Which is newer?

GPT-5 Mini is the newest, released Aug 7, 2025. Qwen3 235B-A22B Thinking 2507 came out Jul 25, 2025; Gemini 2.5 Flash Preview 05-20 came out May 20, 2025. Knowledge cutoff: Gemini 2.5 Flash Preview 05-20 Jan 2025, GPT-5 Mini May 30, 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 Nov 2, 2026.

05 — Keep comparing

Related comparisons