ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Gemini 3 Flash Preview vs GLM-5.2 vs Grok 4.20 (Reasoning)

Gemini 3 Flash Preview comes out ahead, 73 to 68 and 61 on our weighted score, and it is the cheaper option too.

  1. Our pick

    Google

    Gemini 3 Flash Preview

    Released Dec 17, 2025

    73/100
    • ECI151.8
    • Price$0.50 / $3.00
    • Context1.05M
    Full specs Remove Gemini 3 Flash Preview

  2. Z.ai (Zhipu)

    GLM-5.2

    Released Jun 13, 2026

    61/100
    • ECI151.8
    • Price$1.40 / $4.40
    • Context1M
    Full specs Remove GLM-5.2

  3. xAI

    Grok 4.20 (Reasoning)

    Released Mar 9, 2026

    68/100
    • ECI152.0
    • Price$1.25 / $2.50
    • Context1M
    Full specs Remove Grok 4.20 (Reasoning)
01 — Verdict

Gemini 3 Flash Preview is our pick

Gemini 3 Flash Preview is the better all-round choice, scoring 73/100 against Grok 4.20 (Reasoning) (68) and GLM-5.2 (61). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGrok 4.20 (Reasoning)Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.0 · Gemini 3 Flash Preview 151.8 · GLM-5.2 151.8
  • Lowest priceGemini 3 Flash PreviewGemini 3 Flash Preview $1.13 · Grok 4.20 (Reasoning) $1.56 · GLM-5.2 $2.15 per 1M tokens (3:1 blend)
  • Longest contextGemini 3 Flash PreviewGemini 3 Flash Preview 1,048,576 · GLM-5.2 1,000,000 · Grok 4.20 (Reasoning) 1,000,000 tokens
  • Widest inputsGemini 3 Flash PreviewGemini 3 Flash Preview: Text, Images, PDFs, Audio, Video · GLM-5.2: Text · Grok 4.20 (Reasoning): Text, Images, PDFs
  • Self-hostingGLM-5.2Publishes downloadable weights
How the score is built
MeasureWeightGemini 3 Flash PreviewGLM-5.2Grok 4.20 (Reasoning)
CapabilityCapabilities Index (ECI)50%808081
Price25%473441
Inputs & features15%1004580
Context window10%616060
Overall100%73/10061/10068/100
02 — Side by side

Every spec in one table

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

Gemini 3 Flash Preview vs GLM-5.2 vs Grok 4.20 (Reasoning) specifications side by side
SpecificationGemini 3 Flash PreviewGoogleGLM-5.2Z.ai (Zhipu)Grok 4.20 (Reasoning)xAI
Capability
Capabilities Index (ECI)151.8151.8152.0 (best)
ECI rank#43 of 148#44 of 148#41 of 148 (best)
GPQA DiamondGraduate-level science questions89.4%91.9% (best)89.3%
FrontierMath Tiers 1–3Research-level mathematics51.2%59.2% (best)44.9%
OTIS Mock AIME 2024–2025Competition mathematics95.6% (best)86.4%92.2%
SWE-bench VerifiedFixing real GitHub issues75.4%78.7% (best)—
SimpleQA VerifiedShort factual questions66.8% (best)34.2%30.2%
Price per million tokens
Input$0.50 (best)$1.40$1.25
Output$3.00$4.40$2.50 (best)
Cached input$0.05 (best)$0.26$0.20
Blended (3:1)$1.13 (best)$2.15$1.56
Long-context rateSame rateSame rateOver 200K: $2.50 / $5.00
Price sourceOfficial Google APIOfficial Z.AI APIOfficial xAI API
Limits
Context window1,048,576 tokens (best)1,000,000 tokens1,000,000 tokens
Max output65,536 tokens131,072 tokens (best)30,000 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioYesNoNo
VideoYesNoNo
ReasoningYesminimal · low · medium · highYeshigh · maxYes
Tool callingYesYesYes
Structured outputYesYesYes
Availability
WeightsProprietaryOpenProprietary
API model IDgemini-3-flash-previewglm-5.2grok-4.20-0309-reasoning
API providers2080 (best)11
ReleasedDec 17, 2025Jun 13, 2026Mar 9, 2026
Knowledge cutoffJan 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.

  • Gemini 3 Flash Preview$11.00
  • GLM-5.2$22.80
  • Grok 4.20 (Reasoning)$17.50
04 — Questions

Which should you choose?

Which is better: Gemini 3 Flash Preview, GLM-5.2 or Grok 4.20 (Reasoning)?

Gemini 3 Flash Preview is the better all-round choice, scoring 73/100 against Grok 4.20 (Reasoning) (68) and GLM-5.2 (61). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemini 3 Flash Preview, GLM-5.2 or Grok 4.20 (Reasoning)?

Gemini 3 Flash Preview is cheaper at $0.50 input / $3.00 output per million tokens (official Google API price). Grok 4.20 (Reasoning) costs $1.25 input / $2.50 output per million tokens (official xAI API price); GLM-5.2 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $1.13 per million tokens for Gemini 3 Flash Preview versus $1.56 for Grok 4.20 (Reasoning) (1.4× as much) and $2.15 for GLM-5.2 (1.9× as much).

Which scores higher on benchmarks?

Grok 4.20 (Reasoning) scores higher on the Capabilities Index (ECI): Grok 4.20 (Reasoning) 152.0 (#41 of 148), Gemini 3 Flash Preview 151.8 (#43 of 148) and GLM-5.2 151.8 (#44 of 148). The confidence ranges of the top two overlap (149.3–154.4 vs 150.4–153.7), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5.2 91.9%, Gemini 3 Flash Preview 89.4%, Grok 4.20 (Reasoning) 89.3%; FrontierMath Tiers 1–3 — GLM-5.2 59.2%, Gemini 3 Flash Preview 51.2%, Grok 4.20 (Reasoning) 44.9%; OTIS Mock AIME 2024–2025 — Gemini 3 Flash Preview 95.6%, Grok 4.20 (Reasoning) 92.2%, GLM-5.2 86.4%; SimpleQA Verified — Gemini 3 Flash Preview 66.8%, GLM-5.2 34.2%, Grok 4.20 (Reasoning) 30.2%.

Which is better for coding?

There are no published SWE-bench Verified results for Grok 4.20 (Reasoning) yet, so there is no like-for-like coding score. On overall capability, Grok 4.20 (Reasoning) 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 3 Flash Preview has the largest context window at 1,048,576 tokens, against 1,000,000 for GLM-5.2 and 1,000,000 for Grok 4.20 (Reasoning). Maximum output per response: Gemini 3 Flash Preview up to 65,536, GLM-5.2 up to 131,072, Grok 4.20 (Reasoning) up to 30,000 tokens.

Which can read images, PDFs, audio or video?

Gemini 3 Flash Preview accepts text, images, PDFs, audio and video; GLM-5.2 accepts text; Grok 4.20 (Reasoning) accepts text, images and PDFs. Gemini 3 Flash Preview handles the widest range of inputs.

Are any of these open source?

GLM-5.2 publishes its weights and can be self-hosted; Gemini 3 Flash Preview and Grok 4.20 (Reasoning) is proprietary.

Which is newer?

GLM-5.2 is the newest, released Jun 13, 2026. Grok 4.20 (Reasoning) came out Mar 9, 2026; Gemini 3 Flash Preview came out Dec 17, 2025. Knowledge cutoff: Gemini 3 Flash Preview 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