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 Claude Sonnet 5

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

Claude Sonnet 5

Anthropic · Claude Sonnet

Composite 62Intel 5510 rows2 sources

Anthropic's June 2026 Sonnet-class release. Artificial Analysis Intelligence Index 53.4 at max adaptive effort — between GPT-5.5 and Claude Opus 4.7 on the public AA board. API list price $2 / $10 per 1M tokens.

Gemini 3.7 Flash6stats won

Tied1stats

Claude Sonnet 50stats won

Spec showdown

Capacity, price, freshness.

Gemini 3.7 FlashvsClaude Sonnet 5

Composite scores are within 5 points — 67 for Gemini 3.7 Flash vs 62 for Claude Sonnet 5. The choice comes down to capability profile and price. Gemini 3.7 Flash has the higher Vals/AA intelligence score (56 vs 55). Gemini 3.7 Flash is more affordable at $0.75/1M input — about 3× cheaper than $2.0/1M.

Composite score
Gemini 3.7 Flash67Winner on this rowClaude Sonnet 562
Intelligence (Vals/AA)
Gemini 3.7 Flash56Winner on this rowClaude Sonnet 555
Context window
Gemini 3.7 Flash1MClaude Sonnet 51M
Max output
Gemini 3.7 Flash64KWinner on this rowClaude Sonnet 5—
Input price / 1M (lower wins)
Gemini 3.7 Flash$0.75Winner on this rowClaude Sonnet 5$2.0
Output speed (AA default API)
Gemini 3.7 Flash307 t/sWinner on this rowClaude Sonnet 580 t/s
Time to first token (AA default API)
Gemini 3.7 Flash7.00sWinner on this rowClaude Sonnet 5142.07s

Composite score

Intelligence (Vals/AA)

Context window

Max output

64K

—

Input price / 1M (lower wins)

$0.75

$2.0

Output speed (AA default API)

307 t/s

80 t/s

Time to first token (AA default API)

7.00s

142.07s

Capability grid

What each model can do.

Modalities

Gemini 3.7 FlashClaude Sonnet 5

Text●●

Image●—

Audio●—

Video●—

Code●●

Tool use●●

Reasoning●●

Access

Gemini 3.7 FlashClaude Sonnet 5

API●●

Consumer app●●

Open weights——

Managed cloud●●

On-device——

Family profile

Top score per benchmark family.

Reasoning

Coding

Agentic

Long context

Benchmark ranks

Every shared benchmark, side by side.

Reasoning

Artificial Analysis Intelligence Index#18/184 · #21/184

56%

55.3%

GPQA Diamond#3/185 · #30/185

94.5%

91.1%

Humanity's Last Exam#8/180 · #27/180

47.9%

41.3%

Coding

SciCode#5/180 · #20/180

56.8%

53.6%

Agentic

Terminal-Bench#9/184 · #22/184

85.77%

80.52%

τ³-Bench Banking#32/106 · #23/106

32.78%

37.32%

Long context

AA-LCR#6/179 · #27/179

80%

77%

Performance

AA output speed#6/185 · #49/185

307 t/s

80 t/s

AA time to first token#16/185 · #1/185

7.00s

142.07s

Dossier facts

Dates, sources, fineprint.

Gemini 3.7 FlashClaude Sonnet 5

ProviderGoogleAnthropic

FamilyGemini 3.7Claude Sonnet

Release date2026-08-132026-06-30

Knowledge cutoffunpublishedopen

Context window1M1M

Max output64K—

Input price /1M$0.75$2.0

Output price /1M$3.8$10

Statusflagshipsolid

Composite score6762

Intelligence score5655

Intel sourceaaaa

Benchmark rows1010

Source count12

Freshnessfreshfresh

Pricing checked2026-08-132026-07-09

Ecosystem

Which tools wrap each model.

Gemini 3.7 Flash

gemini

Claude Sonnet 5

claude

Verdict

Which model to actually pick.

Open Gemini 3.7 Flash's dossier Open Claude Sonnet 5's dossier