Model release comparison

Gemini 3.7 Flash vs GLM-5.3

Publisher-reported figures, side by side. The shared benchmark is not confirmed to use the same harness.

Google

Gemini 3.7 Flash

Gemini 3.7 Flash: Routable on MiniRouter

Read the dossier
Z.ai

GLM-5.3

GLM-5.3: Routable on MiniRouter

Read the dossier
Attributes

Head to head

AttributeGemini 3.7 FlashGLM-5.3
VendorGoogleZ.ai
AnnouncedAug 13, 2026Aug 14, 2026
API price / 1M in / out$0.75 / $3.75Not published
WeightsNot in announcementZ.ai says weights will follow two weeks after launch
Reasoning effortNot covered in announcementlow / high / max
DeepSWE v1.1

The one shared benchmark

Both figures are publisher-reported. Google and Z.ai may have used different harnesses, settings or environments.
Gemini 3.7 Flash
65.3%
GLM-5.3
66.9%
Reported gap
1.6pp
Not a ranking: identical harnesses are unconfirmed.

Price-performance field

DeepSWE v1.1 scores against a 3:1 input-output blended price. The two publisher runs may use different harnesses, so position is orientation—not a rank.

Price as published · Aug 14, 2026

DeepSWE v1.1 publisher-reported scores against blended API price. Gemini 3.7 Flash is 65.3 percent at 1 dollar 50 introductory and 3 dollars standard per million blended tokens. GLM-5.3 is 66.9 percent with no published price.

Price not published

GLM-5.3

Blended price = 0.75 × input price + 0.25 × output price. Filled squares are currently routable; hollow squares are not. GLM-5.3 remains on the unpriced rail instead of receiving an estimate.

Visible table equivalent of the field. Publisher-reported results; no overall rank is assigned.
ModelCatalogPrice phaseBlended / 1MDeepSWE v1.1Reported bySource
Gemini 3.7 FlashYesIntroductory$1.5065.3%GoogleGoogle ↗
Gemini 3.7 FlashYesStandard$3.0065.3%GoogleGoogle ↗
GLM-5.3Yes—Not published66.9%Z.aiZ.ai ↗
Pricing

Published price comparison

Gemini 3.7 Flash · introductory blended$1.50 / 1M

3:1 input-output mix; introductory phase ends Dec 31, 2026.

GLM-5.3Not published

No price is inferred from GLM-5.2 or any third-party listing.

Caveats

What is not independently confirmed

  • [ 01 ]

    Publisher-reported results and independent measurements are labeled separately. MiniRouter did not run these benchmarks.

  • [ 02 ]

    Benchmark harnesses are not standardised. Results sharing a name across vendors have not been confirmed to use identical runs.

  • [ 03 ]

    Publisher pricing can change, and introductory phases have stated end dates.

  • [ 04 ]

    Catalog status is shown per model above. Dossier coverage is not a commitment to keep any route available.

Sources

Sources

Editorial reference revised 2026-11-12. Catalog status comes from the generated routing snapshot.
  1. Gemini 4 Hydrogen model cardPublished Nov 12, 2026Read at Google DeepMind ↗
  2. Google Gemini 4 Carbon announcementPublished Oct 28, 2026Read at Google ↗
  3. Anthropic Claude Fable 5.2 announcementPublished Nov 9, 2026Read at Anthropic ↗
  4. Meta Muse Ember announcementPublished Nov 9, 2026Read at Meta ↗
  5. Particle-1 announcementPublished Oct 28, 2026Read at Particle AI ↗
  6. Vercel Joey-1 listingPublished Oct 29, 2026Read at Vercel ↗
  7. OpenAI GPT-6.1 Terra announcementPublished Oct 26, 2026Read at OpenAI ↗
  8. Moonshot Kimi K3.1 Pro announcementPublished Oct 23, 2026Read at Moonshot AI ↗
  9. DeepSeek V4.1 Flash 1017 announcementPublished Oct 17, 2026Read at DeepSeek ↗
  10. Meta Muse Spark Open announcementPublished Oct 15, 2026Read at Meta ↗
  11. Google Gemini 4 Argon announcementPublished Sep 30, 2026Read at Google ↗
  12. Meta Muse Wonder announcementPublished Oct 12, 2026Read at Meta ↗
  13. Anthropic Haiku 5.5 announcementPublished Oct 7, 2026Read at Anthropic ↗
  14. Mistral Large 4 public preview announcementPublished Oct 6, 2026Read at Mistral AI ↗
  15. Google Nano Banana 2.1 model documentationPublished Oct 6, 2026Read at Google ↗
  16. OpenAI GPT-6.1 Sol documentationPublished Sep 29, 2026Read at OpenAI ↗
  17. Anthropic Sonnet 5.5 announcementPublished Sep 28, 2026Read at Anthropic ↗
  18. SpaceXAI Grok 4.7 announcementPublished Sep 21, 2026Read at SpaceXAI ↗
  19. StepFun Step 5 Preview announcementPublished Sep 20, 2026Read at StepFun ↗
  20. PrismML Bonsai 2 announcementPublished Sep 17, 2026Read at PrismML ↗
  21. DeepSeek V4.1 Flash model cardPublished Sep 10, 2026Read at DeepSeek ↗
  22. OpenAI GPT-6 Astra announcementPublished Sep 3, 2026Read at OpenAI ↗
  23. Google announcementPublished Aug 13, 2026Read at Google ↗
  24. Z.ai announcementPublished Aug 14, 2026Read at Z.ai ↗
  25. DeepSeek GA release notesPublished Aug 13, 2026Read at DeepSeek ↗
  26. xAI announcementPublished Aug 12, 2026Read at xAI ↗
  27. Meta AI Research announcementPublished Aug 10, 2026Read at Meta ↗
  28. Alibaba Cloud announcementPublished Aug 3, 2026Read at Alibaba Cloud ↗
  29. Moonshot AI announcementPublished Aug 8, 2026Read at Moonshot AI ↗
  30. MiniMax announcementPublished Aug 9, 2026Read at MiniMax ↗
  31. OpenAI GPT-5.6 announcementPublished Jul 9, 2026Read at OpenAI ↗
  32. OpenAI announcementPublished Aug 11, 2026Read at OpenAI ↗
  33. Google announcementPublished Sep 2, 2026Read at Google ↗
  34. Alibaba Cloud Model Studio model pagePublished Sep 2, 2026Read at Alibaba Cloud ↗
  35. Anthropic announcementPublished Sep 1, 2026Read at Anthropic ↗
  36. Tencent Hy4 preview model cardPublished Aug 28, 2026Read at Tencent ↗
  37. Z.ai announcementPublished Aug 26, 2026Read at Z.ai ↗
  38. Qwen3.8-Flash-Next release notesPublished Aug 26, 2026Read at Alibaba ↗
  39. DeepSeek model cardPublished Aug 21, 2026Read at DeepSeek ↗
Explore

Keep reading

Every model, one key.