Head-to-head comparison

Gemini 3.7 Flash vs. DeepSeek-V4-Pro

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 20
distinct benchmarks: 20
latest retrieval: 2026-09-29

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Gemini 3.7 Flash and DeepSeek-V4-Pro
Attribute	Gemini 3.7 Flash	DeepSeek-V4-Pro
Provider	Google	DeepSeek
Released	Aug 13, 2026	Apr 24, 2026
Availability	Active	Active
Model type	Proprietary	Open Weights
Parameters	Not published	1.6T, 49B active
Architecture	Not published	Mixture of Experts
Context window	1,048,576 tokens	1,000,000 tokens
Knowledge cutoff	March 2026	Not published
Technical sources	Model, Knowledge cutoff	Model, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Gemini 3.7 Flash and DeepSeek-V4-Pro
Price type	Gemini 3.7 Flash	DeepSeek-V4-Pro
API input	$0.75	$0.66 (Off-Peak)
API output	$3.75	$1.98 (Off-Peak)
Cache read	$0.07	$0.02 (Off-Peak)
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source
DeepSeek-V4-Pro: peak pricing is $1.32 input / $3.96 output per 1M tokens during Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC; off-peak rates apply at all other times.

Gemini 3.7 FlashDeepSeek-V4-Pro

API inputUSD per 1M tokens, base tier

Gemini 3.7 Flash$0.75

DeepSeek-V4-Pro$0.66

API outputUSD per 1M tokens, base tier

Gemini 3.7 Flash$3.75

DeepSeek-V4-Pro$1.98

Cache readUSD per 1M tokens, base tier

Gemini 3.7 Flash$0.075

DeepSeek-V4-Pro$0.022

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Gemini 3.7 Flash and DeepSeek-V4-Pro
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Gemini 3.7 Flash	Google	Direct from developerStandard API	$0.75	$3.75	Source09/22/2026
	Google	Via OpenRoutergoogle-vertex/global	$0.75	$3.75	Source10/02/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source10/02/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$1.35	$6.75	Source10/02/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$0.75	$3.75	Source10/02/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source10/02/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$1.35	$6.75	Source10/02/2026
DeepSeek-V4-Pro	DeepSeek	Direct from developerStandard API	$0.66	$1.98	Source09/22/2026
	Alibaba	Via OpenRouteralibaba	$0.5808	$1.7424	Source10/02/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$1.32	$3.96	Source10/02/2026
	Baidu	Via OpenRouterbaidu/fp8	Lowest listed price: $0.132	Lowest listed price: $0.396	Source10/02/2026
	Cloudflare	Via OpenRoutercloudflare	$1.32	$3.96	Source10/02/2026
	CoreWeave	Via OpenRoutercoreweave/fp8	$1.31	$3.96	Source10/02/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$1.3	$2.6	Source10/02/2026
	DeepSeek	Via OpenRouterdeepseek	$0.66	$1.98	Source10/02/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.32	$3.96	Source10/02/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.056	$3.168	Source10/02/2026
	Ionstream	Via OpenRouterionstream	$0.2127	$1.7424	Source10/02/2026
	NextBit	Via OpenRouternextbit/fp8	$1.056	$3.168	Source10/02/2026
	Novita	Via OpenRouternovita/fp8	$0.99	$2.97	Source10/02/2026
	Parasail	Via OpenRouterparasail/fp8	$1.32	$3.96	Source10/02/2026
	Phala	Via OpenRouterphala	$0.957	$2.8776	Source10/02/2026
	Relace	Via OpenRouterrelace/fp4	$0.9	$2.7	Source10/02/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.32	$3.96	Source10/02/2026
	StreamLake	Via OpenRouterstreamlake	$0.66	$1.98	Source10/02/2026
	Together	Via OpenRoutertogether	$1.32	$3.96	Source10/02/2026
	Venice	Via OpenRoutervenice	$1.65	$4.95	Source10/02/2026
	Wafer	Via OpenRouterwafer	$0.33	$4.2	Source10/02/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Gemini 3.7 Flash

DeepSeek-V4-Pro

Coding: 100 / 88.1 (5 benchmark families)

Reasoning: 100 / 95.2 (1 benchmark family)

Mathematics: 100 / 27.6 (1 benchmark family)

Knowledge: 100 / 96.8 (1 benchmark family)

Finance: 99.6 / 85.9 (4 benchmark families)

Legal: 100 / 67.2 (3 benchmark families)

Agentic tasks: 100 / 71.3 (2 benchmark families)

Health: 100 / 82.6 (2 benchmark families)

20 matched rows from 20 benchmark families were considered. The radar shows 8 of 9 comparable categories.

Gemini 3.7 FlashDeepSeek-V4-Pro

Code MigrationOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash34.8 %

DeepSeek-V4-Pro26.201 %

EMBOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash71.326 %

DeepSeek-V4-Pro51.623 %

Finance Agent (v2)Overall. Higher is better. No documented setup difference

Gemini 3.7 Flash59.042 %

DeepSeek-V4-Pro44.083 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash93.94 %

DeepSeek-V4-Pro89.394 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference

Gemini 3.7 Flash8.75 %

DeepSeek-V4-Pro3.75 %

Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference

Gemini 3.7 Flash34.615 %

DeepSeek-V4-Pro23.077 %

LegalBenchOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash87.256 %

DeepSeek-V4-Pro80.323 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Gemini 3.7 Flash88.652 %

DeepSeek-V4-Pro87.484 %

MedCodeOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash53.39 %

DeepSeek-V4-Pro40.455 %

MedScribeOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash83.942 %

DeepSeek-V4-Pro75.144 %

MMLU-ProOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash90.121 %

DeepSeek-V4-Pro87.249 %

ProgramBenchOverall. Higher is better. No documented setup difference

Gemini 3.7 Flash0 %

DeepSeek-V4-Pro0 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.7 Flash and DeepSeek-V4-Pro
Benchmark and task	Gemini 3.7 Flash	DeepSeek-V4-Pro	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner34.8 %	26.201 %	Vals AI Source details Data as of: 09/27/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner71.326 %	51.623 %	Vals AI Source details Data as of: 09/27/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner59.042 %	44.083 %	Vals AI Source details Data as of: 09/27/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner93.94 %	89.394 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better	Winner8.75 %	3.75 %	Vals AI Source details Data as of: 09/27/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better	Winner34.615 %	23.077 %	Vals AI Source details Data as of: 09/27/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner87.256 %	80.323 %	Vals AI Source details Data as of: 09/27/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner88.652 %	87.484 %	Vals AI Source details Data as of: 09/01/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner53.39 %	40.455 %	Vals AI Source details Data as of: 09/26/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner83.942 %	75.144 %	Vals AI Source details Data as of: 09/26/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner90.121 %	87.249 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Tie0 %	Tie0 %	Vals AI Source details Data as of: 09/27/2026
ProofBenchOverall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	Winner58 %	16 %	Vals AI Source details Data as of: 09/28/2026
SkillsBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	Winner65.891 %	51.274 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner80.8 %	77.4 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	57.665 %	Winner58.499 %	Vals AI Source details Data as of: 09/27/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner74.734 %	72.077 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	Winner77.528 %	50.187 %	Vals AI Source details Data as of: 09/27/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better	Winner59.307 %	42.888 %	Vals AI Source details Data as of: 09/27/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	Winner70.395 %	49.931 %	Vals AI Source details Data as of: 09/27/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Gemini 3.7 Flash

API access was unavailable for this run. The model was not evaluated.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: google/gemini-3.7-flash
Reasoning setting: high
Pinned endpoint: Google AI Studio | google/gemini-3.7-flash-20260813
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

DeepSeek-V4-Pro

API access was unavailable for this run. The model was not evaluated.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: deepseek/deepseek-v4-pro-0813
Reasoning setting: high
Pinned endpoint: DeepSeek | deepseek/deepseek-v4-pro-20260813
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare Gemini 3.7 Flash and DeepSeek-V4-Pro with other leading models using the same data and benchmark logic.

View the complete LLM comparison