Head-to-head comparison

Claude Opus 4.8 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: 249
distinct benchmarks: 25
latest retrieval: 2026-10-15

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 Claude Opus 4.8 and DeepSeek-V4-Pro
Attribute	Claude Opus 4.8	DeepSeek-V4-Pro
Provider	Anthropic	DeepSeek
Released	May 2026	Apr 24, 2026
Availability	Legacy	Active
Model type	Proprietary	Open Weights
Parameters	Not published	1.6T, 49B active
Architecture	Not published	Mixture of Experts
Context window	1,000,000 tokens	1,000,000 tokens
Knowledge cutoff	January 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 Claude Opus 4.8 and DeepSeek-V4-Pro
Price type	Claude Opus 4.8	DeepSeek-V4-Pro
API input	$5	$0.66 (Off-Peak)
API output	$25	$1.98 (Off-Peak)
Cache read	$0.5	$0.022 (Off-Peak)
Cache write (5 min.)	$6.25	Not listed
Cache write (1 hr.)	$10	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.

Claude Opus 4.8DeepSeek-V4-Pro

API inputUSD per 1M tokens, base tier

Claude Opus 4.8$5

DeepSeek-V4-Pro$0.66

API outputUSD per 1M tokens, base tier

Claude Opus 4.8$25

DeepSeek-V4-Pro$1.98

Cache readUSD per 1M tokens, base tier

Claude Opus 4.8$0.5

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.

No provider tariff for Claude Opus 4.8 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Opus 4.8 and DeepSeek-V4-Pro
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Opus 4.8	Anthropic	Direct from developerStandard API	Lowest listed price: $5	Lowest listed price: $25	Source09/22/2026
DeepSeek-V4-Pro	DeepSeek	Direct from developerStandard API	$0.66	$1.98	Source09/22/2026
	Alibaba	Via OpenRouteralibaba	$1.122	$3.366	Source10/17/2026
	Alibaba	Via OpenRouteralibaba/us-east-1	$1.32	$3.96	Source10/17/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$1.32	$3.96	Source10/17/2026
	Baidu	Via OpenRouterbaidu/fp8	Lowest listed price: $0.2495	Lowest listed price: $0.7484	Source10/17/2026
	Cloudflare	Via OpenRoutercloudflare	$1.32	$3.96	Source10/17/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$1.3	$2.6	Source10/17/2026
	DeepSeek	Via OpenRouterdeepseek	$0.66	$1.98	Source10/17/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.32	$3.96	Source10/17/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.056	$3.168	Source10/17/2026
	Ionstream	Via OpenRouterionstream	$0.37	$2.93	Source10/17/2026
	Novita	Via OpenRouternovita/fp8	$0.99	$2.97	Source10/17/2026
	Parasail	Via OpenRouterparasail/fp8	$1.32	$3.96	Source10/17/2026
	Phala	Via OpenRouterphala	$1.45	$4.36	Source10/17/2026
	Sail Research	Via OpenRoutersail-research/fp4	$0.448	$1.164	Source10/17/2026
	Sail Research	Via OpenRoutersail-research/us	$0.448	$1.164	Source10/17/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.32	$3.96	Source10/17/2026
	StreamLake	Via OpenRouterstreamlake	$0.66	$1.98	Source10/17/2026
	Together	Via OpenRoutertogether	$1.32	$3.96	Source10/17/2026
	Venice	Via OpenRoutervenice	$1.65	$4.95	Source10/17/2026
	Wafer	Via OpenRouterwafer/mxfp4	$0.25	$5	Source10/17/2026

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.

Claude Opus 4.8

DeepSeek-V4-Pro

Coding: 100 / 95.9 (2 benchmark families)

Reasoning: 100 / 97.8 (1 benchmark family)

Mathematics: 100 / 97.8 (1 benchmark family)

Knowledge: 100 / 97.8 (1 benchmark family)

Finance: 100 / 97.7 (1 benchmark family)

Legal: 100 / 98.5 (1 benchmark family)

Health: 100 / 98.9 (1 benchmark family)

General: 100 / 98.3 (1 benchmark family)

66 matched rows from 2 benchmark families were considered. The radar shows 8 of 8 comparable categories.

Claude Opus 4.8DeepSeek-V4-Pro

Code MigrationOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.847.25 %

DeepSeek-V4-Pro26.201 %

CorpFin v2Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.866.706 %

DeepSeek-V4-Pro61.383 %

EMBOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.869.373 %

DeepSeek-V4-Pro51.623 %

Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.918 %

DeepSeek-V4-Pro44.083 %

GPQA DiamondOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.892.424 %

DeepSeek-V4-Pro89.394 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical

Claude Opus 4.89.583 %

DeepSeek-V4-Pro3.75 %

Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical

Claude Opus 4.843.75 %

DeepSeek-V4-Pro23.077 %

LegalBenchOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.883.568 %

DeepSeek-V4-Pro80.323 %

LiveCodeBench v6Overall. Higher is better. Test setup not documented as identical

Claude Opus 4.887.819 %

DeepSeek-V4-Pro87.484 %

LMArena Code Arena WebDevOverall. Higher is better. No documented setup difference

Claude Opus 4.81,536.177

DeepSeek-V4-Pro1,446.815

LMArena Text, Style ControlOverall. Higher is better. No documented setup difference

Claude Opus 4.81,474.25

DeepSeek-V4-Pro1,457.848

MedCodeOverall. Higher is better. Test setup not documented as identical

Claude Opus 4.853.217 %

DeepSeek-V4-Pro40.455 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 4.8 and DeepSeek-V4-Pro
Benchmark and task	Claude Opus 4.8	DeepSeek-V4-Pro	Source
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value47.25 %	26.201 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value66.706 %	61.383 %	Vals AI Source details Data as of: 08/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value69.373 %	51.623 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value53.918 %	44.083 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.424 %	89.394 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value9.583 %	3.75 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value43.75 %	23.077 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value83.568 %	80.323 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value87.819 %	87.484 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 14,023 published pairwise votes.	Winner1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,446.815 95% confidence interval: ±6.319The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 65,181 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 57,614 published pairwise votes.	Winner1,474.25 95% confidence interval: ±3.848The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,457.848 95% confidence interval: ±3.899The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MedCodeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value53.217 %	40.455 %	Vals AI Source details Data as of: 10/13/2026
MedScribeOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value85.755 %	75.144 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value89.585 %	87.249 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value1 %	0 %	Vals AI Source details Data as of: 10/12/2026
Public Benefits Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value68.133 %	62.923 %	Vals AI Source details Data as of: 10/12/2026
SkillsBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Harness: OpenHands, Output limit: 384,000 tokens	Higher measured value59.227 %	51.274 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench VerifiedOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value88.6 %	77.4 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value29.999 %	25.17 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value75.634 %	72.077 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value70.037 %	56.18 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value71.91 %	50.187 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value23.232 %	11.111 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexOverall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: weighted index scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value55.1 %	38.63 %	Vals AI Source details Data as of: 10/13/2026
Vibe Code Bench v1.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Harness: OpenHands, Output limit: 256,000 tokens	Higher measured value82.725 %	49.931 %	Vals AI Source details Data as of: 10/12/2026
Code MigrationCLI Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value40.143 %	15.47 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value64.336 %	59.207 %	Vals AI Source details Data as of: 08/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value72.797 %	57.434 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Adjustments Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value48.387 %	41.586 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value91.919 %	90.404 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value87.319 %	83.696 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value43.939 %	28.788 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	88.937 %	Higher measured value89.117 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value99.068 %	98.758 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 18,540 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 13,199 published pairwise votes.	Winner1,555.99 95% confidence interval: ±5.768The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,463.849 95% confidence interval: ±6.309The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 64,112 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 54,929 published pairwise votes.	Winner1,481.505 95% confidence interval: ±3.87The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,454.814 95% confidence interval: ±3.964The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value94.7 %	92.887 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value15.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
SkillsBenchNo Skills Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Harness: OpenHands, Output limit: 384,000 tokens	Higher measured value43.674 %	27.226 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.784 %	87.629 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value13.133 %	12.333 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value64.513 %	60.589 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value91.667 %	75 %	Vals AI Source details Data as of: 06/04/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value100 %	66.667 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Hardware Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value26.667 %	0 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value46.942 %	26.212 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCOBOL Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value68.571 %	58.393 %	Vals AI Source details Data as of: 10/12/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value69.814 %	63.054 %	Vals AI Source details Data as of: 08/12/2026
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value85.948 %	62.572 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)All-Pass Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value43.517 %	31.448 %	Vals AI Source details Data as of: 10/12/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.929 %	88.384 %	Vals AI Source details Data as of: 09/01/2026
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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value87.365 %	83.372 %	Vals AI Source details Data as of: 10/12/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value82.703 %	75.169 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value74.571 %	72.571 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 14,023 published pairwise votes.	Winner1,536.177 95% confidence interval: ±5.702The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,446.815 95% confidence interval: ±6.319The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 12,774 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 11,383 published pairwise votes.	Winner1,486.06 95% confidence interval: ±6.336The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,459.786 95% confidence interval: ±6.716The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value92.649 %	91.888 %	Vals AI Source details Data as of: 09/01/2026
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value1 %	0 %	Vals AI Source details Data as of: 10/12/2026
SkillsBenchWith Skills Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Harness: OpenHands, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Harness: OpenHands, Output limit: 384,000 tokens	Higher measured value59.227 %	51.274 %	Vals AI Source details Data as of: 09/27/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens	Higher measured value66.667 %	0 %	Vals AI Source details Data as of: 09/01/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value58.743 %	54.843 %	Vals AI Source details Data as of: 10/12/2026
TaxEval v2Stepwise Reasoning Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value86.754 %	83.565 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value54.444 %	33.333 %	Vals AI Source details Data as of: 06/04/2026
Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 4ae5d8eeb9a9

Claude Opus 4.8

Unavailable in this round

DeepSeek-V4-Pro

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Claude Opus 4.8

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-opus-4.8
API model reported in response: anthropic/claude-opus-4.8
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.8-opus-20260528
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Response time: 18 s

Visually reviewed. This individual test does not establish overall model quality.

DeepSeek-V4-Pro

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

Reasoning (requested): high

Current attempt

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: deepseek/deepseek-v4-pro-0813
API model reported in response: 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: Failed
Response time: 67.6 s

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

Earlier attempts (3)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high
Sep 7, 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 Claude Opus 4.8 and DeepSeek-V4-Pro with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Opus 4.8 vs. DeepSeek-V4-Pro

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Opus 4.8

DeepSeek-V4-Pro

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons