VerdictPal · editorial desk · updated 5 Sep 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 3.8 Flash vs Gemini 3.7 Flash

Model A

Model B

MODEL A

Gemini 3.8 Flash

Google · Gemini 3.8

Composite 47Intel 471 rows1 sources

Google's 2 Sep 2026 Flash workhorse. Same intro API price as 3.7 Flash: $0.75 / $3.75 per 1M tokens through 31 Dec 2026. 1M context, 64K output. AA Intelligence Index v4.2 is 47 at high effort — two points above 3.7 Flash on the same scale.

MODEL B

Gemini 3.7 Flash

Google · Gemini 3.7

Composite 65Intel 4510 rows1 sources

Google's August 2026 Flash workhorse, superseded as the current Flash by Gemini 3.8 Flash on 2 Sep 2026. Live AA Intelligence Index v4.2 is 45 at high effort (was 56 on the v4.1 snapshot). Introductory API price still $0.75 / $3.75 per 1M tokens through 31 Dec 2026.

Gemini 3.8 Flash2stats won

Tied3stats

Gemini 3.7 Flash2stats won

Spec showdown

Capacity, price, freshness.

Gemini 3.8 FlashvsGemini 3.7 Flash

Gemini 3.7 Flash leads on composite score (65 vs 47), with deeper benchmark coverage across more families. Gemini 3.8 Flash has the higher Vals/AA intelligence score (47 vs 45).

Composite score
Gemini 3.8 Flash47Gemini 3.7 Flash65Winner on this row
Intelligence (Vals/AA)
Gemini 3.8 Flash47Winner on this rowGemini 3.7 Flash45
Context window
Gemini 3.8 Flash1MGemini 3.7 Flash1M
Max output
Gemini 3.8 Flash64KGemini 3.7 Flash64K
Input price / 1M (lower wins)
Gemini 3.8 Flash$0.75Gemini 3.7 Flash$0.75
Output speed (AA default API)
Gemini 3.8 Flash—Gemini 3.7 Flash307 t/sWinner on this row
Time to first token (AA default API)
Gemini 3.8 Flash—Winner on this rowGemini 3.7 Flash7.00s

Composite score

Intelligence (Vals/AA)

Context window

Max output

64K

Input price / 1M (lower wins)

$0.75

Output speed (AA default API)

—

307 t/s

Time to first token (AA default API)

—

7.00s

Capability grid

What each model can do.

Modalities

Gemini 3.8 FlashGemini 3.7 Flash

Text●●

Image●●

Audio●●

Video●●

Code●●

Tool use●●

Reasoning●●

Access

Gemini 3.8 FlashGemini 3.7 Flash

API●●

Consumer app●●

Open weights——

Managed cloud●●

On-device——

Family profile

Top score per benchmark family.

Reasoning

Benchmark ranks

Every shared benchmark, side by side.

Reasoning

Artificial Analysis Intelligence Index#42/187 · #49/187

47%

45%

Dossier facts

Dates, sources, fineprint.

Gemini 3.8 FlashGemini 3.7 Flash

ProviderGoogleGoogle

FamilyGemini 3.8Gemini 3.7

Release date2026-09-022026-08-13

Knowledge cutoff2026-03-01unpublished

Context window1M1M

Max output64K64K

Input price /1M$0.75$0.75

Output price /1M$3.8$3.8

Statusflagshipflagship

Composite score4765

Intelligence score4745

Intel sourceaaaa

Benchmark rows110

Source count11

Freshnessfreshfresh

Pricing checked2026-09-052026-09-05

Ecosystem

Which tools wrap each model.

Gemini 3.8 Flash

gemini

Gemini 3.7 Flash

gemini

Verdict

Which model to actually pick.

Gemini 3.7 Flash leads on composite score (65 vs 47), with deeper benchmark coverage across more families. Gemini 3.8 Flash has the higher Vals/AA intelligence score (47 vs 45).

Open Gemini 3.8 Flash's dossier Open Gemini 3.7 Flash's dossier