Head-to-head comparison

Muse Spark 1.3 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: 201
distinct benchmarks: 22
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 Muse Spark 1.3 and DeepSeek-V4-Pro
Attribute	Muse Spark 1.3	DeepSeek-V4-Pro
Provider	Meta	DeepSeek
Released	Sep 2, 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	Not published	Not published
Technical sources	Model, Context	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 Muse Spark 1.3 and DeepSeek-V4-Pro
Price type	Muse Spark 1.3	DeepSeek-V4-Pro
API input	$1.25	$0.66 (Off-Peak)
API output	$4.25	$1.98 (Off-Peak)
Cache read	$0.15	$0.022 (Off-Peak)
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	10/18/2026 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.

Muse Spark 1.3DeepSeek-V4-Pro

API inputUSD per 1M tokens, base tier

Muse Spark 1.3$1.25

DeepSeek-V4-Pro$0.66

API outputUSD per 1M tokens, base tier

Muse Spark 1.3$4.25

DeepSeek-V4-Pro$1.98

Cache readUSD per 1M tokens, base tier

Muse Spark 1.3$0.15

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 Muse Spark 1.3 and DeepSeek-V4-Pro
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Muse Spark 1.3	Meta	Via OpenRoutermeta	Lowest listed price: $1.25	Lowest listed price: $4.25	Source10/18/2026
DeepSeek-V4-Pro	DeepSeek	Direct from developerStandard API	$0.66	$1.98	Source09/22/2026
	Alibaba	Via OpenRouteralibaba/us-east-1	$1.32	$3.96	Source10/18/2026
	AtlasCloud	Via OpenRouteratlas-cloud/fp8	$1.32	$3.96	Source10/18/2026
	Baidu	Via OpenRouterbaidu/fp8	$0.1333	Lowest listed price: $0.4	Source10/18/2026
	Cloudflare	Via OpenRoutercloudflare	$1.32	$3.96	Source10/18/2026
	CoreWeave	Via OpenRoutercoreweave/fp8	$1.31	$3.96	Source10/18/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$1.3	$2.6	Source10/18/2026
	DeepSeek	Via OpenRouterdeepseek	$0.66	$1.98	Source10/18/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.32	$3.96	Source10/18/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.056	$3.168	Source10/18/2026
	Ionstream	Via OpenRouterionstream	$0.37	$2.93	Source10/18/2026
	Novita	Via OpenRouternovita/fp8	$0.99	$2.97	Source10/18/2026
	Parasail	Via OpenRouterparasail/fp8	$1.32	$3.96	Source10/18/2026
	Phala	Via OpenRouterphala	$0.957	$2.8776	Source10/18/2026
	Relace	Via OpenRouterrelace/fp4	Lowest listed price: $0.12	$8	Source10/18/2026
	Sail Research	Via OpenRoutersail-research/fp4	$0.448	$1.164	Source10/18/2026
	Sail Research	Via OpenRoutersail-research/us	$0.448	$1.164	Source10/18/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.32	$3.96	Source10/18/2026
	StreamLake	Via OpenRouterstreamlake	$0.66	$1.98	Source10/18/2026
	Together	Via OpenRoutertogether	$1.32	$3.96	Source10/18/2026
	Venice	Via OpenRoutervenice	$1.65	$4.95	Source10/18/2026
	Wafer	Via OpenRouterwafer/mxfp4	$0.25	$2.5	Source10/18/2026

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.

Muse Spark 1.3

DeepSeek-V4-Pro

Coding: 100 / 42.4 (1 benchmark family)

Reasoning: 100 / 74.6 (3 benchmark families)

Knowledge: 100 / 3.3 (1 benchmark family)

Agentic tasks: 100 / 87.9 (3 benchmark families)

Overall: 100 / 74.8 (1 benchmark family)

9 matched rows from 9 benchmark families were considered. The radar shows 5 of 5 comparable categories.

Muse Spark 1.3DeepSeek-V4-Pro

AA-BriefcaseOverall. Higher is better. No documented setup difference

Muse Spark 1.31,581.34 elo

DeepSeek-V4-Pro1,256.94 elo

AA-LCROverall. Higher is better. No documented setup difference

Muse Spark 1.383.0%

DeepSeek-V4-Pro80.3%

AA-OmniscienceOverall. Higher is better. No documented setup difference

Muse Spark 1.325 points

DeepSeek-V4-Pro0.833 points

Artificial Analysis Intelligence IndexOverall. Higher is better. No documented setup difference

Muse Spark 1.348.092 points

DeepSeek-V4-Pro35.997 points

AutomationBench-AAOverall. Higher is better. No documented setup difference

Muse Spark 1.357.9%

DeepSeek-V4-Pro56.7%

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

Muse Spark 1.327.58 %

DeepSeek-V4-Pro26.201 %

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

Muse Spark 1.362.712 %

DeepSeek-V4-Pro51.623 %

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

Muse Spark 1.358.901 %

DeepSeek-V4-Pro44.083 %

GDP.pdfOverall. Higher is better. No documented setup difference

Muse Spark 1.326.6%

DeepSeek-V4-Pro11.4%

GDPval-AAOverall. Higher is better. No documented setup difference

Muse Spark 1.31,680.99 elo

DeepSeek-V4-Pro1,450.47 elo

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

Muse Spark 1.322.917 %

DeepSeek-V4-Pro3.75 %

Humanity's Last ExamOverall. Higher is better. No documented setup difference

Muse Spark 1.348.7%

DeepSeek-V4-Pro41.0%

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Muse Spark 1.3 and DeepSeek-V4-Pro
Benchmark and task	Muse Spark 1.3	DeepSeek-V4-Pro	Source
AA-BriefcaseOverall Test details No documented difference in the test setupVersion: v1.1Metric: AA-Briefcase EloScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner1,581.34 elo	1,256.94 elo	Artificial Analysis Source details Data as of: 10/15/2026
AA-LCROverall Test details No documented difference in the test setupVersion: v1.1Metric: Pass rateScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner83.0%	80.3%	Artificial Analysis Source details Data as of: 10/15/2026
AA-OmniscienceOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: AA-Omniscience IndexScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner25 points The index can be negative and ranges from -100 to 100 according to Artificial Analysis.	0.833 points The index can be negative and ranges from -100 to 100 according to Artificial Analysis.	Artificial Analysis Source details Data as of: 10/15/2026
Artificial Analysis Intelligence IndexOverall Test details No documented difference in the test setupVersion: v4.3.2Metric: Artificial Analysis Intelligence IndexScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner48.092 points	35.997 points	Artificial Analysis Source details Data as of: 10/15/2026
AutomationBench-AAOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: Objectives completed without guardrail violationsScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner57.9%	56.7%	Artificial Analysis Source details Data as of: 10/15/2026
Code MigrationOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value27.58 %	26.201 %	Vals AI Source details Data as of: 10/12/2026
EMBOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value62.712 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value58.901 %	44.083 %	Vals AI Source details Data as of: 10/12/2026
GDP.pdfOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: All-pass rateScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner26.6%	11.4%	Artificial Analysis Source details Data as of: 10/15/2026
GDPval-AAOverall Test details No documented difference in the test setupVersion: v2.1Metric: GDPval-AA EloScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner1,680.99 elo	1,450.47 elo	Artificial Analysis Source details Data as of: 10/15/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value22.917 %	3.75 %	Vals AI Source details Data as of: 10/12/2026
Humanity's Last ExamOverall Test details No documented difference in the test setupVersion: unspecifiedMetric: Text-only pass@1 accuracyScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner48.7% Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.	41.0% Artificial Analysis describes this comparable run as 2,158 text-only questions, not the full 2,500-question dataset.	Artificial Analysis Source details Data as of: 10/15/2026
Legal Research BenchOverall · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value40.865 %	23.077 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMuse Spark 1.3: Snapshot: muse-spark-1.3-max, Reasoning: max, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Text, style controlMuse Spark 1.3: Arena rating from 16,731 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 57,614 published pairwise votes.	Higher measured value1,494.213 95% confidence interval: ±5.665The 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
ProgramBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value0.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
ProofBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1.1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens	Higher measured value55 %	16 %	Vals AI Source details Data as of: 10/12/2026
Tax Agent BenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value35.974 %	25.17 %	Vals AI Source details Data as of: 10/12/2026
Terminal-BenchOverall Test details No documented difference in the test setupVersion: 4.0Metric: Task successScoring: Higher is betterMuse Spark 1.3: Snapshot: Muse Spark 1.3 (Max), Reasoning: Max DeepSeek-V4-Pro: Snapshot: DeepSeek V4 Pro 0813 (Max), Reasoning: MaxMuse Spark 1.3: Exact AA configuration: Muse Spark 1.3 (Max) (release muse-spark-1-3, row muse-spark-1-3, UUID 9999672c-b687-4026-9c15-5cef02ff53bb, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.DeepSeek-V4-Pro: Exact AA configuration: DeepSeek V4 Pro 0813 (Max) (release deepseek-v4-pro, row deepseek-v4-pro, UUID 83173329-c09a-41f1-a028-a282a5f908d7, reasoning=true, source reasoning-token configuration budget=2000, suffix=Max). This configured value is not measured token consumption.	Winner33.3%	14.1%	Artificial Analysis Source details Data as of: 10/15/2026
Terminal-Bench 2.1Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value72.285 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	10.606 %	Higher measured value11.111 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value53.197 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Harness: OpenHands, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Harness: OpenHands, Output limit: 256,000 tokens	Higher measured value82.859 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	13.916 %	Higher measured value15.47 %	Vals AI Source details Data as of: 10/12/2026
EMBComps Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value64.798 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value52.818 %	41.586 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: criteria pass rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value96.377 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value51.515 %	28.788 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMuse Spark 1.3: Snapshot: muse-spark-1.3-max, Reasoning: max, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena Text, style controlMuse Spark 1.3: Arena rating from 16,731 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 54,929 published pairwise votes.	Higher measured value1,494.213 95% confidence interval: ±5.665The 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
ProgramBenchAlmost Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: almost-resolved rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value13 %	0 %	Vals AI Source details Data as of: 10/12/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value14.667 %	12.333 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value75 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexCode Migration Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value42.192 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 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
EMBDataroom Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value84.191 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value48.737 %	31.448 %	Vals AI Source details Data as of: 10/12/2026
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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value20 %	0 %	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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value85.884 %	83.372 %	Vals AI Source details Data as of: 10/12/2026
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 betterMuse Spark 1.3: Snapshot: muse-spark-1.3-max, Reasoning: max, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Text, style controlMuse Spark 1.3: Arena rating from 3,041 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 11,383 published pairwise votes.	Higher measured value1,503.61 95% confidence interval: ±11.102The 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
ProgramBenchFully Resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: fully resolved rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value0.5 %	0 %	Vals AI Source details Data as of: 10/12/2026
Tax Agent BenchControversy & Precedence Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value60.859 %	54.843 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value61.111 %	31.111 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0Media Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner0 %	No direct winner0 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexEMB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value62.712 %	51.623 %	Vals AI Source details Data as of: 10/13/2026
Code MigrationCode Quality Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value4.02 / 5	3.401 / 5	Vals AI Source details Data as of: 10/12/2026
EMBDCF Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value55.697 %	44.435 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Comparables Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value47.167 %	39.632 %	Vals AI Source details Data as of: 10/12/2026
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 betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value93.907 %	83.513 %	Vals AI Source details Data as of: 10/12/2026
Legal Research BenchBusiness & Commercial · All-pass Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: all-pass rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value32.558 %	23.256 %	Vals AI Source details Data as of: 10/12/2026
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 betterMuse Spark 1.3: Snapshot: muse-spark-1.3-max, Reasoning: max, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena Text, style controlMuse Spark 1.3: Arena rating from 3,041 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 11,045 published pairwise votes.	Higher measured value1,503.61 95% confidence interval: ±11.102The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,448.007 95% confidence interval: ±6.811The 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
ProgramBenchRaw Pass Rate Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: raw test pass rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value71.722 %	47.778 %	Vals AI Source details Data as of: 10/12/2026
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value49.769 %	36.595 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 2.1Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens	Higher measured value78.182 %	59.394 %	Vals AI Source details Data as of: 09/28/2026
Terminal-Bench 4.0ML Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value21.212 %	3.03 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexFinance Agent v2 Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value58.901 %	44.083 %	Vals AI Source details Data as of: 10/13/2026
EMBLBO Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value56.579 %	43.938 %	Vals AI Source details Data as of: 10/12/2026
Finance Agent (v2)Disclosure Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value66.693 %	52.649 %	Vals AI Source details Data as of: 10/12/2026
Harvey's Legal Agent BenchmarkArbitration International Dispute Resolution · Task fully resolved Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: task resolution rateScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 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 BenchBusiness & Commercial · Weighted partial credit Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: weighted partial-credit scoreScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value88.24 %	86.491 %	Vals AI Source details Data as of: 10/12/2026
LMArena Text, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMuse Spark 1.3: Snapshot: muse-spark-1.3-max, Reasoning: max, Harness: Arena Text, style control DeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena Text, style controlMuse Spark 1.3: Arena rating from 1,298 published pairwise votes.DeepSeek-V4-Pro: Arena rating from 3,378 published pairwise votes.	Higher measured value1,529.417 95% confidence interval: ±16.859The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,488.803 95% confidence interval: ±10.784The 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
Tax Agent BenchCurrent & Temporal Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value73.142 %	65.741 %	Vals AI Source details Data as of: 10/12/2026
Terminal-Bench 4.0Operations Test details Test setup not documented as identicalNo direct winnerVersion: 4.0Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	No direct winner7.407 %	No direct winner7.407 %	Vals AI Source details Data as of: 10/13/2026
Vals IndexHLAB Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: benchmark scoreScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value22.917 %	3.75 %	Vals AI Source details Data as of: 10/13/2026
EMBM&A Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterMuse Spark 1.3: Reasoning: xhigh, Temperature: 1, Output limit: 131,072 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens	Higher measured value64.366 %	48.156 %	Vals AI Source details Data as of: 10/12/2026
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

Muse Spark 1.3

Unavailable in this round

DeepSeek-V4-Pro

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

Muse Spark 1.3

Reasoning (requested): high

Current attempt

Run date: Oct 2, 2026
API provider: openrouter
Requested API model: meta/muse-spark-1.3
API model reported in response: meta/muse-spark-1.3
Reasoning setting: high
Pinned endpoint: Meta | meta/muse-spark-1.3-20260902
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: 87.9 s

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

Earlier attempts (2)

Oct 1, 2026Output withheld for safetyReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

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 Muse Spark 1.3 and DeepSeek-V4-Pro with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Muse Spark 1.3 vs. DeepSeek-V4-Pro

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Muse Spark 1.3

DeepSeek-V4-Pro

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons