Head-to-head comparison

DeepSeek-V4-Pro vs. MiMo-V2.5

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

shared result series: 130
distinct benchmarks: 19
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 DeepSeek-V4-Pro and MiMo-V2.5
Attribute	DeepSeek-V4-Pro	MiMo-V2.5
Provider	DeepSeek	Xiaomi
Released	Apr 24, 2026	Apr 23, 2026
Availability	Preview	Open Source
Model type	Open Weights	Open Weights
Parameters	1.6T, 49B active	Not published
Architecture	Mixture of Experts	Mixture of Experts
Context window	1,000,000 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 DeepSeek-V4-Pro and MiMo-V2.5
Price type	DeepSeek-V4-Pro	MiMo-V2.5
API input	$0.43	$0.14
API output	$0.87	$0.28
Cache read	$0.	$0.
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	07/30/2026 Source	07/31/2026 Source

DeepSeek-V4-ProMiMo-V2.5

API inputUSD per 1M tokens, base tier

DeepSeek-V4-Pro$0.435

MiMo-V2.5$0.14

API outputUSD per 1M tokens, base tier

DeepSeek-V4-Pro$0.87

MiMo-V2.5$0.28

Cache readUSD per 1M tokens, base tier

DeepSeek-V4-Pro$0.004

MiMo-V2.5$0.003

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

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

Provider pricing for DeepSeek-V4-Pro and MiMo-V2.5
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
DeepSeek-V4-Pro	DeepSeek	Direct from developerStandard API	Lowest listed price: $0.435	Lowest listed price: $0.87	Source07/30/2026
	Alibaba	Via OpenRouteralibaba	$0.5808	$1.7424	Source09/06/2026
	Baidu	Via OpenRouterbaidu/fp8	$1.1194	$3.3581	Source09/06/2026
	BaseTen	Via OpenRouterbaseten/fp4#1	$1.32	$3.96	Source09/06/2026
	BaseTen	Via OpenRouterbaseten/fp4#2	$1.32	$3.96	Source09/06/2026
	Cloudflare	Via OpenRoutercloudflare	$1.32	$3.96	Source09/06/2026
	CoreWeave	Via OpenRoutercoreweave/fp8	$1.31	$3.96	Source09/06/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$1.3	$2.6	Source09/06/2026
	DeepSeek	Via OpenRouterdeepseek	$0.66	$1.98	Source09/06/2026
	DigitalOcean	Via OpenRouterdigitalocean	$1.32	$3.96	Source09/06/2026
	Fireworks	Via OpenRouterfireworks	$1.32	$3.96	Source09/06/2026
	GMICloud	Via OpenRoutergmicloud/fp8	$1.122	$3.366	Source09/06/2026
	NextBit	Via OpenRouternextbit/fp8	$1.32	$3.96	Source09/06/2026
	Novita	Via OpenRouternovita/fp8	$1.32	$3.96	Source09/06/2026
	Parasail	Via OpenRouterparasail/fp8	$1.32	$3.96	Source09/06/2026
	Phala	Via OpenRouterphala	$1.45	$4.36	Source09/06/2026
	Sail Research	Via OpenRoutersail-research/fp4	$1.32	$3.96	Source09/06/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.32	$3.96	Source09/06/2026
	StreamLake	Via OpenRouterstreamlake	$0.5795	$1.7384	Source09/06/2026
	Together	Via OpenRoutertogether	$1.32	$3.96	Source09/06/2026
MiMo-V2.5	Xiaomi	Direct from developerStandard API	$0.14	$0.28	Source07/31/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$0.13	$0.65	Source09/06/2026
	GMICloud	Via OpenRoutergmicloud/fp8	Lowest listed price: $0.119	Lowest listed price: $0.238	Source09/06/2026
	Novita	Via OpenRouternovita/fp8	$0.168	$0.336	Source09/06/2026
	StreamLake	Via OpenRouterstreamlake	$0.168	$0.336	Source09/06/2026
	Xiaomi	Via OpenRouterxiaomi/fp8	$0.14	$0.28	Source09/06/2026

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.

DeepSeek-V4-Pro

MiMo-V2.5

Coding: 100 / 84.6 (5 benchmark families)

Reasoning: 100 / 95.2 (2 benchmark families)

Mathematics: 100 / 99.8 (2 benchmark families)

Knowledge: 100 / 96.8 (2 benchmark families)

Finance: 98.7 / 95.8 (5 benchmark families)

Legal: 100 / 69.8 (4 benchmark families)

Agentic tasks: 82.7 / 100 (1 benchmark family)

Health: 100 / 91 (3 benchmark families)

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

DeepSeek-V4-ProMiMo-V2.5

Code MigrationOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro26.201 %

MiMo-V2.514.228 %

CorpFin v2Overall. Higher is better. No documented setup difference

DeepSeek-V4-Pro61.383 %

MiMo-V2.559.907 %

EMBOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro51.623 %

MiMo-V2.555.092 %

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

DeepSeek-V4-Pro44.083 %

MiMo-V2.536.728 %

GPQA DiamondOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro89.394 %

MiMo-V2.581.566 %

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

DeepSeek-V4-Pro3.75 %

MiMo-V2.51.667 %

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

DeepSeek-V4-Pro23.077 %

MiMo-V2.59.135 %

LegalBenchOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro80.323 %

MiMo-V2.578.886 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

DeepSeek-V4-Pro87.484 %

MiMo-V2.581.512 %

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

DeepSeek-V4-Pro1,457.748

MiMo-V2.51,433.798

MedCodeOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro40.455 %

MiMo-V2.531.895 %

MedScribeOverall. Higher is better. No documented setup difference

DeepSeek-V4-Pro75.144 %

MiMo-V2.572.151 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for DeepSeek-V4-Pro and MiMo-V2.5
Benchmark and task	DeepSeek-V4-Pro	MiMo-V2.5	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner26.201 %	14.228 %	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	Winner61.383 %	59.907 %	Vals AI Source details Data as of: 08/12/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	51.623 %	Winner55.092 %	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	Winner44.083 %	36.728 %	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	Winner89.394 %	81.566 %	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	Winner3.75 %	1.667 %	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	Winner23.077 %	9.135 %	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	Winner80.323 %	78.886 %	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	Winner87.484 %	81.512 %	Vals AI Source details Data as of: 09/01/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 54,243 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 44,540 anonymous pairwise votes.	Winner1,457.748 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.	1,433.798 95% confidence interval: ±4.342The 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	Winner40.455 %	31.895 %	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	Winner75.144 %	72.151 %	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	Winner87.249 %	82.931 %	Vals AI Source details Data as of: 09/01/2026
ProofBenchOverall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	Tie16 %	Tie16 %	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	Winner77.4 %	71 %	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	Winner72.077 %	71.832 %	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	50.187 %	Winner60.674 %	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	Winner42.888 %	39.91 %	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	Winner49.931 %	42.174 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value15.47 %	9.88 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	59.207 %	Higher measured value59.441 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value41.586 %	31.746 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value90.404 %	79.798 %	Vals AI Source details Data as of: 08/09/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value89.117 %	86.386 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value98.758 %	98.447 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 51,599 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 44,540 anonymous pairwise votes.	Higher measured value1,455.047 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.	1,433.798 95% confidence interval: ±4.342The 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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value92.887 %	90.237 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value87.629 %	80.928 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	60.589 %	Higher measured value60.752 %	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 betterDeepSeek-V4-Pro: Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	66.667 %	Higher measured value100 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value61.888 %	60.14 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value58.393 %	27.273 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value63.054 %	60.14 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value31.448 %	23.785 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value88.384 %	83.333 %	Vals AI Source details Data as of: 08/09/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value75.169 %	74.351 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value72.571 %	59.143 %	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 betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 10,742 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,127 anonymous pairwise votes.	Winner1,461.034 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.	1,441.542 95% confidence interval: ±7.42The 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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.888 %	89.227 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	No direct winner0 %	No direct winner0 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value83.565 %	82.911 %	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 betterDeepSeek-V4-Pro: Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	31.111 %	Higher measured value36.667 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value44.081 %	37.61 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value3.401 / 5	2.788 / 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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value61.888 %	60.14 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value39.632 %	31.672 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	84.587 %	Higher measured value86.337 %	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 betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.123 %	86.945 %	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 betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 10,411 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,127 anonymous pairwise votes.	Higher measured value1,448.251 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.	1,441.542 95% confidence interval: ±7.42The 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-ProChemistry Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value92.491 %	89.841 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified1-4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value45.238 %	33.333 %	Vals AI Source details Data as of: 08/08/2026
Terminal-Bench 2.1Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	59.394 %	Higher measured value70.909 %	Vals AI Source details Data as of: 08/06/2026
Vals IndexSWE-bench Test details No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is better	Winner75.49 %	64.706 %	Vals AI Source details Data as of: 08/09/2026
Finance Agent (v2)Disclosure Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value52.649 %	47.346 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchRhetoric Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	75.316 %	Higher measured value77.776 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlChinese Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,871 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,140 anonymous pairwise votes.	No clear lead1,493.385 95% confidence interval: ±11.839The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,483.45 95% confidence interval: ±13.352The 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-ProComputer Science Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value89.024 %	86.585 %	Vals AI Source details Data as of: 08/09/2026
SWE-bench Verified15 min - 1 hour Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value75.862 %	70.498 %	Vals AI Source details Data as of: 08/08/2026
Vals IndexTerminal-Bench 2.1 Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterDeepSeek-V4-Pro: Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	50.187 %	Higher measured value60.674 %	Vals AI Source details Data as of: 08/09/2026
Finance Agent (v2)Earnings Analysis Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value59.84 %	45.006 %	Vals AI Source details Data as of: 08/06/2026
LegalBenchRule Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value77.425 %	69.582 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterDeepSeek-V4-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlDeepSeek-V4-Pro: Style-controlled Arena rating from 2,757 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,140 anonymous pairwise votes.	Higher measured value1,498.025 95% confidence interval: ±12.143The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,483.45 95% confidence interval: ±13.352The 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-ProEconomics Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value88.863 %	86.73 %	Vals AI Source details Data as of: 08/09/2026
Vals IndexVibe Code Bench Test details Test setup not documented as identicalNo direct winnerVersion: 1.2Metric: benchmark scoreScoring: Higher is betterDeepSeek-V4-Pro: Reasoning: max, Output limit: 256,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value55.905 %	48.148 %	Vals AI Source details Data as of: 08/09/2026
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 DeepSeek-V4-Pro and MiMo-V2.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison