Head-to-head comparison

Gemini 3.6 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: 212
distinct benchmarks: 21
latest retrieval: 2026-09-04

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 3.6 Flash and DeepSeek-V4-Pro
Attribute	Gemini 3.6 Flash	DeepSeek-V4-Pro
Provider	Google	DeepSeek
Released	Jul 21, 2026	Apr 24, 2026
Availability	Active	Preview
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	Not published	Not published
Technical sources	Model	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 3.6 Flash and DeepSeek-V4-Pro
Price type	Gemini 3.6 Flash	DeepSeek-V4-Pro
API input	$0.75	$0.43
API output	$3.75	$0.87
Cache read	$0.07	$0.
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	08/16/2026 Source	07/30/2026 Source

Gemini 3.6 FlashDeepSeek-V4-Pro

API inputUSD per 1M tokens, base tier

Gemini 3.6 Flash$0.75

DeepSeek-V4-Pro$0.435

API outputUSD per 1M tokens, base tier

Gemini 3.6 Flash$3.75

DeepSeek-V4-Pro$0.87

Cache readUSD per 1M tokens, base tier

Gemini 3.6 Flash$0.075

DeepSeek-V4-Pro$0.004

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 3.6 Flash and DeepSeek-V4-Pro
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Gemini 3.6 Flash	Google	Direct from developerStandard API	$0.75	$3.75	Source08/16/2026
	Google	Via OpenRoutergoogle-vertex/global	$0.75	$3.75	Source09/07/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source09/07/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$1.35	$6.75	Source09/07/2026
	Google	Via OpenRoutergoogle-vertex/us	$0.825	$4.125	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$0.75	$3.75	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source09/07/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$1.35	$6.75	Source09/07/2026
DeepSeek-V4-Pro	DeepSeek	Direct from developerStandard API	Lowest listed price: $0.435	Lowest listed price: $0.87	Source07/30/2026
	Alibaba	Via OpenRouteralibaba	$1.122	$3.366	Source09/07/2026
	Baidu	Via OpenRouterbaidu/fp8	$1.1194	$3.3581	Source09/07/2026
	BaseTen	Via OpenRouterbaseten/fp4#1	$1.32	$3.96	Source09/07/2026
	BaseTen	Via OpenRouterbaseten/fp4#2	$1.32	$3.96	Source09/07/2026
	Cloudflare	Via OpenRoutercloudflare	$1.32	$3.96	Source09/07/2026
	CoreWeave	Via OpenRoutercoreweave/fp8	$1.31	$3.96	Source09/07/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$1.3	$2.6	Source09/07/2026
	DeepSeek	Via OpenRouterdeepseek	$0.66	$1.98	Source09/07/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.32	$3.96	Source09/07/2026
	Fireworks	Via OpenRouterfireworks	$1.32	$3.96	Source09/07/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.122	$3.366	Source09/07/2026
	NextBit	Via OpenRouternextbit/fp8	$1.32	$3.96	Source09/07/2026
	Novita	Via OpenRouternovita/fp8	$1.32	$3.96	Source09/07/2026
	Parasail	Via OpenRouterparasail/fp8	$1.32	$3.96	Source09/07/2026
	Phala	Via OpenRouterphala	$1.45	$4.36	Source09/07/2026
	Sail Research	Via OpenRoutersail-research/fp4	$1.32	$3.96	Source09/07/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.32	$3.96	Source09/07/2026
	StreamLake	Via OpenRouterstreamlake	$1.1207	$3.362	Source09/07/2026
	Together	Via OpenRoutertogether	$1.32	$3.96	Source09/07/2026

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 3.6 Flash

DeepSeek-V4-Pro

Coding: 100 / 92.9 (6 benchmark families)

Reasoning: 100 / 97.1 (2 benchmark families)

Mathematics: 100 / 98 (1 benchmark family)

Knowledge: 100 / 98.2 (2 benchmark families)

Finance: 100 / 89.7 (5 benchmark families)

Legal: 97.2 / 96 (4 benchmark families)

Agentic tasks: 100 / 68 (1 benchmark family)

Productivity: 89.9 / 100 (1 benchmark family)

50 matched rows from 21 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Gemini 3.6 FlashDeepSeek-V4-Pro

Code MigrationOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash30.928 %

DeepSeek-V4-Pro26.201 %

CorpFin v2Overall. Higher is better. No documented setup difference

Gemini 3.6 Flash63.326 %

DeepSeek-V4-Pro61.383 %

CyberBenchOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash48.514 %

DeepSeek-V4-Pro68.644 %

EMBOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash65.411 %

DeepSeek-V4-Pro51.623 %

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

Gemini 3.6 Flash56.296 %

DeepSeek-V4-Pro44.083 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash93.434 %

DeepSeek-V4-Pro89.394 %

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

Gemini 3.6 Flash3.333 %

DeepSeek-V4-Pro3.75 %

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

Gemini 3.6 Flash25 %

DeepSeek-V4-Pro23.077 %

LegalBenchOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash86.705 %

DeepSeek-V4-Pro80.323 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Gemini 3.6 Flash88.08 %

DeepSeek-V4-Pro87.484 %

LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical

Gemini 3.6 Flash1,480.192

DeepSeek-V4-Pro1,457.748

MedCodeOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash53.153 %

DeepSeek-V4-Pro40.455 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.6 Flash and DeepSeek-V4-Pro
Benchmark and task	Gemini 3.6 Flash	DeepSeek-V4-Pro	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner30.928 %	26.201 %	Vals AI Source details Data as of: 09/03/2026
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner63.326 %	61.383 %	Vals AI Source details Data as of: 08/12/2026
CyberBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	48.514 %	Winner68.644 %	Vals AI Source details Data as of: 09/01/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner65.411 %	51.623 %	Vals AI Source details Data as of: 09/03/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner56.296 %	44.083 %	Vals AI Source details Data as of: 09/03/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner93.434 %	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	3.333 %	Winner3.75 %	Vals AI Source details Data as of: 09/03/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better	Winner25 %	23.077 %	Vals AI Source details Data as of: 09/03/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner86.705 %	80.323 %	Vals AI Source details Data as of: 09/01/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner88.08 %	87.484 %	Vals AI Source details Data as of: 09/01/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 22,009 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 54,243 anonymous pairwise votes.	Higher measured value1,480.192 95% confidence interval: ±5.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,457.748 95% confidence interval: ±4.009The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner53.153 %	40.455 %	Vals AI Source details Data as of: 09/03/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner79.661 %	75.144 %	Vals AI Source details Data as of: 09/03/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner89.276 %	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: 09/01/2026
Public Benefits Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	56.563 %	Winner62.923 %	Vals AI Source details Data as of: 09/01/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner79.6 %	77.4 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner74.857 %	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	Winner73.783 %	50.187 %	Vals AI Source details Data as of: 09/03/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better	Winner55.354 %	42.888 %	Vals AI Source details Data as of: 09/03/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	Winner64.005 %	49.931 %	Vals AI Source details Data as of: 09/03/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value19.332 %	15.47 %	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value61.072 %	59.207 %	Vals AI Source details Data as of: 08/06/2026
CyberBenchPatch Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	Higher measured value84.746 %	79.661 %	Vals AI Source details Data as of: 08/03/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value70.019 %	57.434 %	Vals AI Source details Data as of: 08/06/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value53.608 %	41.586 %	Vals AI Source details Data as of: 08/06/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.424 %	90.404 %	Vals AI Source details Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	79.71 %	Higher measured value83.696 %	Vals AI Source details Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value31.818 %	28.788 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value91.081 %	89.117 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value99.068 %	98.758 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 22,009 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 51,599 anonymous pairwise votes.	Winner1,480.192 95% confidence interval: ±5.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,455.047 95% confidence interval: ±4.08The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value94.7 %	92.887 %	Vals AI Source details Data as of: 08/09/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value2.5 %	0 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	87.113 %	Higher measured value87.629 %	Vals AI Source details Data as of: 08/08/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value63.532 %	60.589 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value100 %	66.667 %	Vals AI Source details Data as of: 08/06/2026
Vals IndexCorpFin v2 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value63.52 %	61.888 %	Vals AI Source details Data as of: 08/09/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value65.714 %	58.393 %	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value65.385 %	63.054 %	Vals AI Source details Data as of: 08/06/2026
CyberBenchPoC Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens	12.281 %	Higher measured value57.627 %	Vals AI Source details Data as of: 08/03/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value72.965 %	62.572 %	Vals AI Source details Data as of: 08/06/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value44.634 %	31.448 %	Vals AI Source details Data as of: 08/06/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value94.444 %	88.384 %	Vals AI Source details Data as of: 08/09/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 08/07/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value83.517 %	83.372 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value83.894 %	75.169 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value74.571 %	72.571 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 4,278 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 10,742 anonymous pairwise votes.	Higher measured value1,477.825 95% confidence interval: ±9.689The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,461.034 95% confidence interval: ±6.908The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.776 %	91.888 %	Vals AI Source details Data as of: 08/09/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value33.333 %	0 %	Vals AI Source details Data as of: 08/08/2026
TaxEval v2Stepwise Reasoning Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value86.182 %	83.565 %	Vals AI Source details Data as of: 08/09/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value64.444 %	31.111 %	Vals AI Source details Data as of: 08/06/2026
Vals IndexFinance Agent v2 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value55.302 %	44.081 %	Vals AI Source details Data as of: 08/09/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	3.299 / 5	Higher measured value3.401 / 5	Vals AI Source details Data as of: 08/09/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value63.52 %	61.888 %	Vals AI Source details Data as of: 08/06/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value59.408 %	44.435 %	Vals AI Source details Data as of: 08/06/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value47.829 %	39.632 %	Vals AI Source details Data as of: 08/06/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	78.853 %	Higher measured value83.512 %	Vals AI Source details Data as of: 08/07/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner23.256 %	No direct winner23.256 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchIssue Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value91.121 %	84.587 %	Vals AI Source details Data as of: 08/09/2026
LiveCodeBench v6Medium Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGemini 3.6 Flash: Reasoning: high, Temperature: 1, Output limit: 65,536 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	90.601 %	Higher measured value91.123 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlBusiness, management and finance Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 4,278 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 10,411 anonymous pairwise votes.	Winner1,477.825 95% confidence interval: ±9.689The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,448.251 95% confidence interval: ±6.986The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
Key to the marks:better valuebetter, but not conclusivetie

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

View the complete LLM comparison