Head-to-head comparison

Gemini 3.1 Pro Preview vs. DeepSeek-V4.1-Flash

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

shared result series: 19
distinct benchmarks: 19
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 3.1 Pro Preview and DeepSeek-V4.1-Flash
Attribute	Gemini 3.1 Pro Preview	DeepSeek-V4.1-Flash
Provider	Google	DeepSeek
Released	Feb 19, 2026	Sep 10, 2026
Availability	Preview	Active
Model type	Proprietary	Open Weights
Parameters	Not published	552B
Architecture	Not published	Mixture of Experts
Context window	1,048,576 tokens	1,000,000 tokens
Knowledge cutoff	Not published	Not published
Technical sources	Model	Model

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 3.1 Pro Preview and DeepSeek-V4.1-Flash
Price type	Gemini 3.1 Pro Preview	DeepSeek-V4.1-Flash
API input	$2 ≤200K / $4 >200K	$0.15 (Off-Peak)
API output	$12 ≤200K / $18 >200K	$0.6 (Off-Peak)
Cache read	$0.2 ≤200K / $0.4 >200K	$0. (Off-Peak)
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/23/2026 Source
DeepSeek-V4.1-Flash: peak pricing is $0.3 input / $1.2 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 3.1 Pro PreviewDeepSeek-V4.1-Flash

API inputUSD per 1M tokens, base tier

Gemini 3.1 Pro Preview$2

DeepSeek-V4.1-Flash$0.15

API outputUSD per 1M tokens, base tier

Gemini 3.1 Pro Preview$12

DeepSeek-V4.1-Flash$0.6

Cache readUSD per 1M tokens, base tier

Gemini 3.1 Pro Preview$0.2

DeepSeek-V4.1-Flash$0.003

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 3.1 Pro Preview and DeepSeek-V4.1-Flash
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Gemini 3.1 Pro Preview	Google	Direct from developerUp to 200,000 context tokens	$2	$12	Source09/22/2026
	Google	Direct from developerAbove 200,000 context tokens	$4	$18	Source09/22/2026
	Google	Via OpenRoutergoogle-vertex/global	$2	$12	Source10/07/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$3.6	$21.6	Source10/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$2	$12	Source10/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $1	Lowest listed price: $6	Source10/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$3.6	$21.6	Source10/07/2026
DeepSeek-V4.1-Flash	DeepSeek	Direct from developerStandard API	$0.15	$0.6	Source09/23/2026
	Alibaba	Via OpenRouteralibaba	$0.3	$1.2	Source10/07/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$0.141	$0.564	Source10/07/2026
	Baidu	Via OpenRouterbaidu/fp8	$0.3	$1.2	Source10/07/2026
	BaseTen	Via OpenRouterbaseten/fp8#1	$0.3	$1.2	Source10/07/2026
	BaseTen	Via OpenRouterbaseten/fp8#2	$0.3	$1.2	Source10/07/2026
	CoreWeave	Via OpenRoutercoreweave/fp8	$0.2	$0.65	Source10/07/2026
	Decart	Via OpenRouterdecart/fp4	$0.09	Lowest listed price: $0.18	Source10/07/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$0.14	$0.42	Source10/07/2026
	DeepSeek	Via OpenRouterdeepseek	$0.3	$1.2	Source10/07/2026
	DekaLLM	Via OpenRouterdekallm	$0.12	$2.4	Source10/07/2026
	DigitalOcean	Via OpenRouterdigitalocean	$0.18	$0.72	Source10/07/2026
	Fireworks	Via OpenRouterfireworks/us	$0.45	$1.8	Source10/07/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$0.18	$0.72	Source10/07/2026
	InferenceNet	Via OpenRouterinference-net/fp8	$0.039	$0.3	Source10/07/2026
	Ionstream	Via OpenRouterionstream	$0.1386	$1.15	Source10/07/2026
	Makora	Via OpenRoutermakora/fp8	$0.27	$1.15	Source10/07/2026
	Modal	Via OpenRoutermodal	$0.3	$1.2	Source10/07/2026
	Morph	Via OpenRoutermorph/fp8	$0.15	$0.471	Source10/07/2026
	Novita	Via OpenRouternovita/fp8	$0.195	$0.78	Source10/07/2026
	Parasail	Via OpenRouterparasail/fp8	$0.3	$1.2	Source10/07/2026
	Phala	Via OpenRouterphala	$0.21	$0.84	Source10/07/2026
	Reka	Via OpenRouterreka	$0.105	$0.84	Source10/07/2026
	Relace	Via OpenRouterrelace	$0.044	$0.3	Source10/07/2026
	Sail Research	Via OpenRoutersail-research/fp4	$0.08	$0.4	Source10/07/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$0.3	$1.2	Source10/07/2026
	StreamLake	Via OpenRouterstreamlake/fp8	$0.141	$0.564	Source10/07/2026
	Together	Via OpenRoutertogether	$0.3	$1.2	Source10/07/2026
	Venice	Via OpenRoutervenice/fp8	$0.3	$1.2	Source10/07/2026
	Wafer	Via OpenRouterwafer	Lowest listed price: $0.038	$1.2	Source10/07/2026

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 3.1 Pro Preview

DeepSeek-V4.1-Flash

Coding: 54.2 / 94.4 (4 benchmark families)

Mathematics: 48.1 / 100 (1 benchmark family)

Finance: 77.6 / 100 (3 benchmark families)

Legal: 50 / 98.4 (3 benchmark families)

Agentic tasks: 95 / 100 (1 benchmark family)

Productivity: 83.7 / 100 (1 benchmark family)

Health: 94.5 / 84.9 (2 benchmark families)

Education: 100 / 98.4 (1 benchmark family)

19 matched rows from 19 benchmark families were considered. The radar shows 8 of 10 comparable categories.

Gemini 3.1 Pro PreviewDeepSeek-V4.1-Flash

BioMysteryBenchOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview60 %

DeepSeek-V4.1-Flash67.778 %

Code MigrationOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview17.313 %

DeepSeek-V4.1-Flash45.623 %

EMBOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview52.616 %

DeepSeek-V4.1-Flash57.208 %

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

Gemini 3.1 Pro Preview42.982 %

DeepSeek-V4.1-Flash53.481 %

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

Gemini 3.1 Pro Preview0 %

DeepSeek-V4.1-Flash6.667 %

IOIOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview51.833 %

DeepSeek-V4.1-Flash40.278 %

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

Gemini 3.1 Pro Preview20.673 %

DeepSeek-V4.1-Flash41.346 %

LegalBenchOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview87.398 %

DeepSeek-V4.1-Flash83.277 %

MedCodeOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview59.062 %

DeepSeek-V4.1-Flash41.173 %

MedScribeOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview76.114 %

DeepSeek-V4.1-Flash85.5 %

MysteryMechanismOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview20.721 %

DeepSeek-V4.1-Flash21.171 %

ProofBenchOverall. Higher is better. No documented setup difference

Gemini 3.1 Pro Preview26 %

DeepSeek-V4.1-Flash54 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.1 Pro Preview and DeepSeek-V4.1-Flash
Benchmark and task	Gemini 3.1 Pro Preview	DeepSeek-V4.1-Flash	Source
BioMysteryBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: Terminus 2	60 %	Winner67.778 %	Vals AI Source details Data as of: 09/27/2026
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	17.313 %	Winner45.623 %	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	52.616 %	Winner57.208 %	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	42.982 %	Winner53.481 %	Vals AI Source details Data as of: 09/27/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better	0 %	Winner6.667 %	Vals AI Source details Data as of: 09/27/2026
IOIOverall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner51.833 %	40.278 %	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	20.673 %	Winner41.346 %	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	Winner87.398 %	83.277 %	Vals AI Source details Data as of: 09/27/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner59.062 %	41.173 %	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	76.114 %	Winner85.5 %	Vals AI Source details Data as of: 09/26/2026
MysteryMechanismOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	20.721 %	Winner21.171 %	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	26 %	Winner54 %	Vals AI Source details Data as of: 09/28/2026
Public Benefits Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	53.789 %	Winner64.276 %	Vals AI Source details Data as of: 09/27/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner48.677 %	47.88 %	Vals AI Source details Data as of: 09/26/2026
Tax Agent BenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	37.842 %	Winner62.458 %	Vals AI Source details Data as of: 09/27/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	70.787 %	Winner74.532 %	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	41.903 %	Winner57.86 %	Vals AI Source details Data as of: 09/27/2026
Vibe Code Bench 1-100Overall Test details No documented difference in the test setupVersion: 1.0Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	6.694 %	Winner16.378 %	Vals AI Source details Data as of: 09/22/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	32.034 %	Winner84.739 %	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 latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Gemini 3.1 Pro Preview

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt

Run date: 2 Oct 2026
API provider: openrouter
Requested API model: google/gemini-3.1-pro-preview
API model reported in response: google/gemini-3.1-pro-preview
Reasoning setting: high
Pinned endpoint: Google AI Studio | google/gemini-3.1-pro-preview-20260219
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 61.6 s

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

Earlier attempts (2)

1 Oct 2026API request failedReasoning setting: high
7 Sept 2026API request failedReasoning setting: high

DeepSeek-V4.1-Flash

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt

Run date: 2 Oct 2026
API provider: openrouter
Requested API model: deepseek/deepseek-v4.1-flash
API model reported in response: deepseek/deepseek-v4.1-flash
Reasoning setting: high
Pinned endpoint: DeepSeek | deepseek/deepseek-v4.1-flash-20260910
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 30.5 s

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

Earlier attempts (1)

1 Oct 2026API request failedReasoning setting: high

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 3.1 Pro Preview and DeepSeek-V4.1-Flash with other leading models using the same data and benchmark logic.

View the complete LLM comparison