none reviewed yet · 2 benchmark observations · latest capture Sep 8, 2026
Inspect the evidenceGoogle · MODEL PROFILE
Gemini 3.6 Flash
High-volume page generation where per-token cost and predictable speed beat frontier reasoning
Saved editorial fit for your current task lens; not a benchmark result
How scoring worksVerified rates (Sep 8, 2026) · 100 runs / month at your token settings
Adjust workloadAt a glance
9 facts- Provider
- Type
- API model
- Access
- Gemini API, Google AI Studio; Standard/Batch/Flex/Priority tiers
- Context
- 1,048,576 tokens
- Maximum output
- n.a. on fetched Google pages
- License / weights
- Proprietary
- Input modalities
- text, image, video, file, audio
- Output modalities
- text
- Pricing notes
- Standard $0.75 in / $3.75 out per 1M through Dec 31, 2026, then $1.50/$7.50; Batch and Flex $0.375/$1.875; Priority $1.35/$6.75
The practical trade-offs
Documented strengths
- Design Arena Website 1317 (rank 7) - visual quality far above its Arena rank
- 208.8 tok/s measured output speed
- $0.75/$3.75 with a free tier
- Largest Gemini Flash vote count in this set (5,932), so its Arena Elo is tightly bounded
Limitations to check
- AA Intelligence 40 is the lowest of the three Gemini Flash entries
- No repo-scale coding benchmark evidence
- Two newer siblings are the same price
- Modalities and max output unstated by Google
Follow the source
6 source linksEvidence & conditions
6Source links
NoneReviewed records
2Benchmark runs
Sep 8, 2026Latest capture
- Evidence source 1
ai.google.devDate not recorded - Evidence source 2
ai.google.devDate not recorded - Evidence source 3
ai.google.devDate not recorded - Evidence source 4
arena.aiDate not recorded - Evidence source 5
benchlm.aiDate not recorded - Evidence source 6
artificialanalysis.aiDate not recorded
Benchmark observations
FrontierCode 1.1 Main Inspect conditions
- name
- FrontierCode 1.1 Main
- value
- 34.4
- unit
- %
- source Url
- https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/
- checked At
- 2026-09-08T19:30:56Z
- attribution
- provider-reported
- configuration
- Google release comparison; exact effort and harness are not specified in the prose.
DeepSWE v1.1 Inspect conditions
- name
- DeepSWE v1.1
- value
- 49
- unit
- %
- source Url
- https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/
- checked At
- 2026-09-08T19:30:56Z
- attribution
- provider-reported
- configuration
- Google release comparison; exact effort and harness are not specified in the prose.
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are shown when recorded; otherwise we say the capture date was not recorded. Recorded dates are compared with this catalogue snapshot (Sep 11, 2026), not today’s date.
Method AIS-V2
How this page is assessed
Quality claims follow Method AIS-V2.
Money never buys rank — commercial relationships cannot change rank, eligibility, evidence quality, or publication timing.
Submit or claim a listing is free and does not skip the editorial queue.
Private · this device only