VerdictPal · editorial desk · updated 16 Oct 2026VerdictPal

Compare · Two models, head-to-head

Pick two models. See the diff.

Composite scores, benchmark ranks, capability grids, and pricing per million tokens. All sourced from the same data that powers the model atlas.

Tools Models

Gemini 3.6 Flash (high) vs Gemini 3.7 Flash

Model A

Model B

MODEL A

Gemini 3.6 Flash (high)

Google · Gemini 3.6

Composite 70Intel 707 rows1 sources

Google introductory API price $0.75 / $3.75 per 1M tokens through 31 Dec 2026; AA still lists $1.50 / $7.50 on the 2026-08-13 snapshot.

MODEL B

Gemini 3.7 Flash

Google · Gemini 3.7

Composite 74Intel 747 rows1 sources

Google's August 2026 Flash workhorse, superseded as the current Flash by Gemini 3.8 Flash on 2 Sep 2026. Introductory API price still $0.75 / $3.75 per 1M tokens through 31 Dec 2026.

Gemini 3.6 Flash (high)0stats won

Tied3stats

Gemini 3.7 Flash3stats won

Spec showdown

Capacity, price, freshness.

Gemini 3.6 Flash (high)vsGemini 3.7 Flash

Composite scores are within 5 points — 70 for Gemini 3.6 Flash (high) vs 74 for Gemini 3.7 Flash. The choice comes down to capability profile and price. Gemini 3.7 Flash has the higher benchmark mix (74 vs 70).

Composite score
Gemini 3.6 Flash (high)70Gemini 3.7 Flash74Winner on this row
Benchmark mix
Gemini 3.6 Flash (high)70Gemini 3.7 Flash74Winner on this row
Context window
Gemini 3.6 Flash (high)1MGemini 3.7 Flash1M
Max output
Gemini 3.6 Flash (high)64KGemini 3.7 Flash64K
Input price / 1M (lower wins)
Gemini 3.6 Flash (high)$0.75Gemini 3.7 Flash$0.75
Output speed (AA default API)
Gemini 3.6 Flash (high)186 t/sGemini 3.7 Flash314 t/sWinner on this row

Composite score

Benchmark mix

Context window

Max output

64K

Input price / 1M (lower wins)

$0.75

Output speed (AA default API)

186 t/s

314 t/s

Capability grid

What each model can do.

Modalities

Gemini 3.6 Flash (high)Gemini 3.7 Flash

Text●●

Image●●

Audio●●

Video●●

Code●●

Tool use●●

Reasoning●●

Access

Gemini 3.6 Flash (high)Gemini 3.7 Flash

API●●

Consumer app●●

Open weights——

Managed cloud●●

On-device——

Family profile

Top score per benchmark family.

Reasoning

Coding

Agentic

Multimodal

Long context

Benchmark ranks

Every shared benchmark, side by side.

Reasoning

GPQA Diamond#19/184 · #5/184

92.8%

94.5%

Humanity's Last Exam#39/186 · #13/186

40.8%

47.9%

Coding

SciCode#32/97 · #13/97

53.4%

57.2%

Agentic

Terminal-Bench#32/167 · #13/167

77.53%

85.77%

Long context

AA-LCR#40/184 · #25/184

80%

81.67%

Performance

AA output speed#22/195 · #4/195

186 t/s

314 t/s

Dossier facts

Dates, sources, fineprint.

Gemini 3.6 Flash (high)Gemini 3.7 Flash

ProviderGoogleGoogle

FamilyGemini 3.6Gemini 3.7

Release date2026-07-212026-08-13

Knowledge cutoffunpublishedunpublished

Context window1M1M

Max output64K64K

Input price /1M$0.75$0.75

Output price /1M$3.8$3.8

Statussolidflagship

Composite score7074

Intelligence score7074

Intel sourcecompositecomposite

Benchmark rows77

Source count11

Freshnessfreshfresh

Pricing checked2026-08-132026-09-05

Ecosystem

Which tools wrap each model.

Gemini 3.6 Flash (high)

gemini

Gemini 3.7 Flash

gemini

Verdict

Which model to actually pick.

Open Gemini 3.6 Flash (high)'s dossier Open Gemini 3.7 Flash's dossier

Questions this comparison answers

Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.

Should you use Gemini 3.6 Flash (high) or Gemini 3.7 Flash?

Is Gemini 3.6 Flash (high) or Gemini 3.7 Flash cheaper?

Gemini 3.6 Flash (high): $0.75 / $3.8. Gemini 3.7 Flash: $0.75 / $3.8.

How do the Gemini 3.6 Flash (high) and Gemini 3.7 Flash context windows compare?

Gemini 3.6 Flash (high): 1M. Gemini 3.7 Flash: 1M.