Head-to-head comparison

GPT-5.4 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: 114
distinct benchmarks: 16
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 GPT-5.4 and MiMo-V2.5
Attribute	GPT-5.4	MiMo-V2.5
Provider	OpenAI	Xiaomi
Released	Mar 2026	Apr 23, 2026
Availability	Active	Open Source
Model type	Proprietary	Open Weights
Parameters	Not published	Not published
Architecture	Not published	Mixture of Experts
Context window	1,050,000 tokens	1,000,000 tokens
Knowledge cutoff	August 31, 2025	Not published
Technical sources	Model	Model, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for GPT-5.4 and MiMo-V2.5
Price type	GPT-5.4	MiMo-V2.5
API input	$2.5 ≤272K / $5 >272K	$0.14
API output	$15 ≤272K / $22.5 >272K	$0.28
Cache read	$0.25 ≤272K / $0.5 >272K	$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

GPT-5.4MiMo-V2.5

API inputUSD per 1M tokens, base tier

GPT-5.4$2.5

MiMo-V2.5$0.14

API outputUSD per 1M tokens, base tier

GPT-5.4$15

MiMo-V2.5$0.28

Cache readUSD per 1M tokens, base tier

GPT-5.4$0.25

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 GPT-5.4 and MiMo-V2.5
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GPT-5.4	OpenAI	Direct from developerUp to 272,000 context tokens	$2.5	$15	Source07/30/2026
	OpenAI	Direct from developerAbove 272,000 context tokens	$5	$22.5	Source07/30/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-east-1	$2.75	$16.5	Source09/07/2026
	Azure	Via OpenRouterazure	$2.5	$15	Source09/07/2026
	Azure	Via OpenRouterazure/eu	$2.75	$16.5	Source09/07/2026
	Azure	Via OpenRouterazure/us	$2.75	$16.5	Source09/07/2026
	OpenAI	Via OpenRouteropenai	$2.5	$15	Source09/07/2026
	OpenAI	Via OpenRouteropenai/fast	$5	$30	Source09/07/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $1.25	Lowest listed price: $7.5	Source09/07/2026
MiMo-V2.5	Xiaomi	Direct from developerStandard API	$0.14	$0.28	Source07/31/2026
	DeepInfra	Via OpenRouterdeepinfra/fp8	$0.13	$0.65	Source09/07/2026
	GMICloud	Via OpenRoutergmicloud/fp8	Lowest listed price: $0.119	Lowest listed price: $0.238	Source09/07/2026
	Novita	Via OpenRouternovita/fp8	$0.168	$0.336	Source09/07/2026
	StreamLake	Via OpenRouterstreamlake	$0.168	$0.336	Source09/07/2026
	Xiaomi	Via OpenRouterxiaomi/fp8	$0.14	$0.28	Source09/07/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

GPT-5.4

MiMo-V2.5

Coding: 100 / 77.9 (5 benchmark families)

Reasoning: 100 / 93.8 (2 benchmark families)

Mathematics: 100 / 98.7 (1 benchmark family)

Knowledge: 100 / 96.5 (2 benchmark families)

Finance: 100 / 93.3 (4 benchmark families)

Legal: 66.7 / 96.1 (3 benchmark families)

Multimodal: 100 / 91.4 (1 benchmark family)

Health: 100 / 89.7 (3 benchmark families)

44 matched rows from 16 benchmark families were considered. The radar shows 8 of 10 comparable categories.

GPT-5.4MiMo-V2.5

Code MigrationOverall. Higher is better. No documented setup difference

GPT-5.434.984 %

MiMo-V2.514.228 %

CorpFin v2Overall. Higher is better. No documented setup difference

GPT-5.465.268 %

MiMo-V2.559.907 %

GPQA DiamondOverall. Higher is better. No documented setup difference

GPT-5.491.666 %

MiMo-V2.581.566 %

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

GPT-5.40 %

MiMo-V2.51.667 %

LegalBenchOverall. Higher is better. No documented setup difference

GPT-5.486.044 %

MiMo-V2.578.886 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

GPT-5.484.141 %

MiMo-V2.581.512 %

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

GPT-5.41,465.527

MiMo-V2.51,433.798

MedCodeOverall. Higher is better. No documented setup difference

GPT-5.441.292 %

MiMo-V2.531.895 %

MedScribeOverall. Higher is better. No documented setup difference

GPT-5.477.549 %

MiMo-V2.572.151 %

MMLU-ProOverall. Higher is better. No documented setup difference

GPT-5.487.482 %

MiMo-V2.582.931 %

MMMU-ProOverall. Higher is better. No documented setup difference

GPT-5.487.514 %

MiMo-V2.580 %

MortgageTaxOverall. Higher is better. No documented setup difference

GPT-5.468.323 %

MiMo-V2.559.26 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.4 and MiMo-V2.5
Benchmark and task	GPT-5.4	MiMo-V2.5	Source
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner34.984 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner65.268 %	59.907 %	Vals AI Source details Data as of: 08/12/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner91.666 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	0 %	Winner1.667 %	Vals AI Source details Data as of: 09/03/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner86.044 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner84.141 %	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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,615 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 44,540 anonymous pairwise votes.	Winner1,465.527 95% confidence interval: ±3.807The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner41.292 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner77.549 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner87.482 %	82.931 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner87.514 %	80 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner68.323 %	59.26 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner43.312 %	43.265 %	Vals AI Source details Data as of: 09/03/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner78.2 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05	Winner73.958 %	71.832 %	Vals AI Source details Data as of: 09/01/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Harness: OpenHands MiMo-V2.5: Harness: OpenHands	Winner67.421 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value23.788 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value64.103 %	59.441 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.414 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value88.939 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value99.068 %	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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,657 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 44,540 anonymous pairwise votes.	Higher measured value1,476.488 95% confidence interval: ±3.881The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 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
MortgageTaxNumerical Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value75.994 %	61.049 %	Vals AI Source details Data as of: 08/09/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens	21.428 %	Higher measured value29.762 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value88.144 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value64.922 %	60.752 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value68.571 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value64.918 %	60.14 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.919 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value83.921 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value67.714 %	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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,060 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,127 anonymous pairwise votes.	Winner1,474.871 95% confidence interval: ±6.534The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.762 %	89.227 %	Vals AI Source details Data as of: 08/09/2026
MortgageTaxSemantic Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value60.652 %	57.472 %	Vals AI Source details Data as of: 08/09/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens	Higher measured value68.826 %	58.762 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.993 %	82.911 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value3.632 / 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value66.783 %	60.14 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value90.526 %	86.337 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	85.64 %	Higher measured value86.945 %	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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,346 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,127 anonymous pairwise votes.	Higher measured value1,483.779 95% confidence interval: ±6.654The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value91.078 %	89.841 %	Vals AI Source details Data as of: 08/09/2026
SAGEPartial Differential Equations Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 30,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 30,000 tokens	39.683 %	Higher measured value41.27 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value50 %	33.333 %	Vals AI Source details Data as of: 08/08/2026
LegalBenchRhetoric Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.824 %	77.776 %	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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,684 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,140 anonymous pairwise votes.	No clear lead1,494.074 95% confidence interval: ±10.702The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value89.756 %	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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value76.245 %	70.498 %	Vals AI Source details Data as of: 08/08/2026
LegalBenchRule Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value84.008 %	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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,482 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,140 anonymous pairwise votes.	Higher measured value1,504.962 95% confidence interval: ±10.923The 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 betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value89.692 %	86.73 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlCoding Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 17,704 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 12,854 anonymous pairwise votes.	Winner1,513.577 95% confidence interval: ±5.956The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,491.02 95% confidence interval: ±6.676The 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-ProEngineering Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value85.243 %	81.011 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlCoding Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 16,441 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 12,854 anonymous pairwise votes.	Higher measured value1,519.961 95% confidence interval: ±6.001The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,491.02 95% confidence interval: ±6.676The 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-ProHealth Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value82.396 %	78.362 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlCreative writing Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,326 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 7,343 anonymous pairwise votes.	Winner1,436.108 95% confidence interval: ±7.048The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,392.817 95% confidence interval: ±8.004The 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-ProHistory Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value79.265 %	68.241 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlCreative writing Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,108 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 7,343 anonymous pairwise votes.	Higher measured value1,443.763 95% confidence interval: ±7.189The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,392.817 95% confidence interval: ±8.004The 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-ProLaw Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value75.477 %	66.757 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlEnglish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 29,058 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 20,213 anonymous pairwise votes.	Winner1,468.527 95% confidence interval: ±4.99The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,452.388 95% confidence interval: ±5.607The 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-ProMath Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-2026-03-05, Reasoning: xhigh, Output limit: 128,000 tokens MiMo-V2.5: Temperature: 1, Top P: 0.95, Output limit: 128,000 tokens	Higher measured value94.671 %	94.004 %	Vals AI Source details Data as of: 08/09/2026
LMArena Text, Style ControlEnglish Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 27,549 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 20,213 anonymous pairwise votes.	Higher measured value1,477.92 95% confidence interval: ±5.043The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,452.388 95% confidence interval: ±5.607The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
Key to the marks:better valuebetter, but not conclusivetie

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare GPT-5.4 and MiMo-V2.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison