VerdictPal · editorial desk · updated 1 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 3.7 Flash vs Gemini 3.6 Flash (high)

Model A

Model B

MODEL A

Gemini 3.7 Flash

Google · Gemini 3.7

Composite 67Intel 5610 rows1 sources

Google's August 2026 Flash workhorse. Artificial Analysis Intelligence Index 56 on the high-effort endpoint. Introductory API price $0.75 / $3.75 per 1M tokens through 31 Dec 2026.

MODEL B

Gemini 3.6 Flash (high)

Google · Gemini 3.6

Composite 63Intel 5210 rows1 sources

AA Intelligence Index 51.6 on the high-effort endpoint. 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.

Gemini 3.7 Flash4stats won

Tied3stats

Gemini 3.6 Flash (high)0stats won

Spec showdown

Capacity, price, freshness.

Gemini 3.7 FlashvsGemini 3.6 Flash (high)

Composite scores are within 5 points — 67 for Gemini 3.7 Flash vs 63 for Gemini 3.6 Flash (high). The choice comes down to capability profile and price. Gemini 3.7 Flash has the higher Vals/AA intelligence score (56 vs 52).

Composite score
Gemini 3.7 Flash67Winner on this rowGemini 3.6 Flash (high)63
Intelligence (Vals/AA)
Gemini 3.7 Flash56Winner on this rowGemini 3.6 Flash (high)52
Context window
Gemini 3.7 Flash1MGemini 3.6 Flash (high)1M
Max output
Gemini 3.7 Flash64KGemini 3.6 Flash (high)64K
Input price / 1M (lower wins)
Gemini 3.7 Flash$0.75Gemini 3.6 Flash (high)$0.75
Output speed (AA default API)
Gemini 3.7 Flash307 t/sWinner on this rowGemini 3.6 Flash (high)161 t/s
Time to first token (AA default API)
Gemini 3.7 Flash7.00sWinner on this rowGemini 3.6 Flash (high)12.64s

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

161 t/s

Time to first token (AA default API)

7.00s

12.64s

Capability grid

What each model can do.

Modalities

Gemini 3.7 FlashGemini 3.6 Flash (high)

Text●●

Image●●

Audio●●

Video●●

Code●●

Tool use●●

Reasoning●●

Access

Gemini 3.7 FlashGemini 3.6 Flash (high)

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

Artificial Analysis Intelligence Index#18/184 · #33/184

56%

51.6%

GPQA Diamond#3/185 · #15/185

94.5%

92.8%

Humanity's Last Exam#8/180 · #31/180

47.9%

40.8%

Coding

SciCode#5/180 · #29/180

56.8%

52.7%

Agentic

Terminal-Bench#9/184 · #32/184

85.77%

77.53%

τ³-Bench Banking#32/106 · #37/106

32.78%

29.9%

Long context

AA-LCR#6/179 · #13/179

80%

79%

Performance

AA output speed#6/185 · #14/185

307 t/s

161 t/s

AA time to first token#16/185 · #12/185

7.00s

12.64s

Dossier facts

Dates, sources, fineprint.

Gemini 3.7 FlashGemini 3.6 Flash (high)

ProviderGoogleGoogle

FamilyGemini 3.7Gemini 3.6

Release date2026-08-132026-07-21

Knowledge cutoffunpublishedunpublished

Context window1M1M

Max output64K64K

Input price /1M$0.75$0.75

Output price /1M$3.8$3.8

Statusflagshipsolid

Composite score6763

Intelligence score5652

Intel sourceaaaa

Benchmark rows1010

Source count11

Freshnessfreshfresh

Pricing checked2026-08-132026-08-13

Ecosystem

Which tools wrap each model.

Gemini 3.7 Flash

gemini

Gemini 3.6 Flash (high)

gemini

Verdict

Which model to actually pick.

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