Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Model A
Gemini 3.6 Flash

Google

75.3/100

Supported · Public rank #9

90% interval 71.2–79.5

Gemini 3.6 Flash vs Gemini 3.7 Flash

Updated August 13, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Gemini 3.7 Flash

Google

—

Evidence status unavailable

90% interval unavailable

Decision reading

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.

1 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Chat turn cost

    1K fresh input + 500 output tokens

    Gemini 3.7 Flash

    Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Gemini 3.6 Flash

    Gemini 3.6 Flash has the lower estimated token cost for this stated workload. Gemini 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Gemini 3.7 Flash

    Gemini 3.7 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
1
Gemini 3.6 Flash only
3
Gemini 3.7 Flash only
14
Like-for-like categories
0 / 8

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Agentic

Not comparable
Gemini 3.6 Flash
83.0
Gemini 3.7 Flash
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Coding

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Knowledge

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Math

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
88.7
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Gemini 3.6 Flash
Not measured
Gemini 3.7 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Gemini 3.6 Flash
$0.00525
Fits in one request
Gemini 3.7 Flash
$0.00262
Fits in one request

Gemini 3.7 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Gemini 3.6 Flash
$0.0975
Fits in one request
Gemini 3.7 Flash
$0.04875
Fits in one request

Gemini 3.7 Flash has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Gemini 3.6 Flash
$0.135
Fits in one request
Gemini 3.7 Flash
$0.2025
Fits in one request
Cached input priced at the published list-input rate

Gemini 3.6 Flash has the lower modeled cost

Gemini 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Provider availability

Gemini 3.6 Flash

Generally Available · Gemini API, Google AI Studio

Google latest Gemini model guide

Gemini 3.7 Flash

Generally Available · Gemini API, Google AI Studio, Google Antigravity, Gemini Enterprise Agent Platform, Gemini Enterprise, Gemini app via Spark

Google Gemini 3.7 Flash launch

Reasoning profile

Gemini 3.6 Flash

Reasoning

Gemini 3.7 Flash

Reasoning

Weight access

Gemini 3.6 Flash

Proprietary

Gemini 3.7 Flash

Proprietary

License

Gemini 3.6 Flash

Proprietary

Gemini 3.7 Flash

Proprietary

Release date

Gemini 3.6 Flash

2026-07-21

Gemini 3.7 Flash

2026-08-13

If you are considering the documented upgrade path
Deployment change
Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner.
Workload cost
Repository review: $0.0975 vs $0.04875. Cache-heavy agent loop: $0.135 vs $0.2025.
Context tradeoff
Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence18 rows

Agentic

  • OSWorld-Verified

    Gemini 3.6 Flash83%
    Source
    Gemini 3.7 Flash—

    Not directly comparable

  • Terminal-Bench 2.1

    Gemini 3.6 Flash—
    Gemini 3.7 Flash85.8%
    Source

    Not directly comparable

  • Terminal-Bench 3.0

    Gemini 3.6 Flash—
    Gemini 3.7 Flash14.9%
    Source

    Not directly comparable

  • AutomationBench

    Gemini 3.6 Flash—
    Gemini 3.7 Flash30.4%
    Source

    Not directly comparable

  • OSWorld 2.0

    Gemini 3.6 Flash—
    Gemini 3.7 Flash47.9%
    Source

    Not directly comparable

  • Agents' Last Exam

    Gemini 3.6 Flash—
    Gemini 3.7 Flash26.3%
    Source

    Not directly comparable

Coding

  • deepSwe

    Gemini 3.6 Flash49%
    Source
    Gemini 3.7 Flash65.3%
    Source

    Gemini 3.7 Flash leads this result

  • cursorBench32

    Gemini 3.6 Flash53.5%
    Source
    Gemini 3.7 Flash—

    Not directly comparable

  • EEBench

    Gemini 3.6 Flash37.4%
    Source
    Gemini 3.7 Flash—

    Not directly comparable

  • FrontierCode 1.1 Main

    Gemini 3.6 Flash—
    Gemini 3.7 Flash43.6%
    Source

    Not directly comparable

  • Terminal-Bench 2.1

    Gemini 3.6 Flash—
    Gemini 3.7 Flash85.8%
    Source

    Not directly comparable

Reasoning

  • GDM-MRCR v2 128K average

    Gemini 3.6 Flash—
    Gemini 3.7 Flash97%
    Source

    Not directly comparable

Knowledge

  • BioMysteryBench (human-solvable)

    Gemini 3.6 Flash—
    Gemini 3.7 Flash87.1%
    Source

    Not directly comparable

  • BioMysteryBench (human-difficult)

    Gemini 3.6 Flash—
    Gemini 3.7 Flash43.5%
    Source

    Not directly comparable

Multimodal

  • GDP.pdf (no tools)

    Gemini 3.6 Flash—
    Gemini 3.7 Flash34.0%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Gemini 3.6 Flash—
    Gemini 3.7 Flash84.5%
    Source

    Not directly comparable

  • CharXiv

    Gemini 3.6 Flash—
    Gemini 3.7 Flash88.7%
    Source

    Not directly comparable

  • LVBench

    Gemini 3.6 Flash—
    Gemini 3.7 Flash85.4%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Gemini 3.6 Flash or Gemini 3.7 Flash?

At least one model is not scored in the current public ranking lane, so the page does not name an overall quality winner. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, Gemini 3.6 Flash or Gemini 3.7 Flash?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Gemini 3.6 Flash or Gemini 3.7 Flash?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Gemini 3.6 Flash or Gemini 3.7 Flash?

For the stated presets, chat costs $0.00525 on Gemini 3.6 Flash and $0.00263 on Gemini 3.7 Flash; repository review costs $0.0975 and $0.04875; the cache-heavy agent loop costs $0.135 and $0.2025. Gemini 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Gemini 3.6 Flash or Gemini 3.7 Flash?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 13, 2026

Watch Gemini 3.6 Flash vs Gemini 3.7 Flash

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.