Skip to main content

Head-to-head comparison

Mistral Large 3 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
29
distinct benchmarks
1
latest retrieval
2026-09-04

Change model selection

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Mistral Large 3 and MiMo-V2.5
AttributeMistral Large 3MiMo-V2.5
ProviderMistral AIXiaomi
ReleasedDec 2, 2025Apr 23, 2026
AvailabilityActiveOpen Source
Model typeOpen WeightsOpen Weights
Parameters675B, 41B activeNot published
ArchitectureMixture of ExpertsMixture of Experts
Context window256,000 tokens1,000,000 tokens
Knowledge cutoffNot publishedNot published
Technical sourcesModelModel, 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 Mistral Large 3 and MiMo-V2.5
Price typeMistral Large 3MiMo-V2.5
API input$0.5$0.14
API output$1.5$0.28
Cache readNot listed$0.
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source07/31/2026 Source
Mistral Large 3MiMo-V2.5
API inputUSD per 1M tokens, base tier
Mistral Large 3$0.5
MiMo-V2.5Lower price$0.14
API outputUSD per 1M tokens, base tier
Mistral Large 3$1.5
MiMo-V2.5Lower price$0.28

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 Mistral Large 3 and MiMo-V2.5
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Mistral Large 3Mistral AIDirect from developerStandard APILowest listed price: $0.5Lowest listed price: $1.5Source07/30/2026
MistralVia OpenRoutermistralLowest listed price: $0.5Lowest listed price: $1.5Source09/07/2026
MistralVia OpenRoutermistral/eu$0.55$1.65Source09/07/2026
MistralVia OpenRoutermistral/zdrLowest listed price: $0.5Lowest listed price: $1.5Source09/07/2026
MiMo-V2.5XiaomiDirect from developerStandard API$0.14$0.28Source07/31/2026
DeepInfraVia OpenRouterdeepinfra/fp8$0.13$0.65Source09/07/2026
GMICloudVia OpenRoutergmicloud/fp8Lowest listed price: $0.119Lowest listed price: $0.238Source09/07/2026
NovitaVia OpenRouternovita/fp8$0.168$0.336Source09/07/2026
StreamLakeVia OpenRouterstreamlake$0.168$0.336Source09/07/2026
XiaomiVia OpenRouterxiaomi/fp8$0.14$0.28Source09/07/2026

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.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalHealthGeneral
Mistral Large 3
MiMo-V2.5
Coding: 98.5 / 100 (1 benchmark family)
Reasoning: 97.4 / 100 (1 benchmark family)
Mathematics: 97.4 / 100 (1 benchmark family)
Knowledge: 97.6 / 100 (1 benchmark family)
Finance: 98 / 100 (1 benchmark family)
Legal: 99.5 / 100 (1 benchmark family)
Health: 98.8 / 100 (1 benchmark family)
General: 98.6 / 99.7 (1 benchmark family)

29 matched rows from 1 benchmark families were considered. The radar shows 8 of 8 comparable categories.

Mistral Large 3MiMo-V2.5
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Mistral Large 31,413.556
MiMo-V2.5Winner1,433.798
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
Mistral Large 31,412.721
MiMo-V2.5Winner1,441.542
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
Mistral Large 31,431.759
MiMo-V2.5Winner1,483.45
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
Mistral Large 31,468.587
MiMo-V2.5Winner1,491.02
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
Mistral Large 31,375.017
MiMo-V2.5Winner1,392.817
LMArena Text, Style ControlEnglish. Higher is better. No documented setup difference
Mistral Large 31,426.818
MiMo-V2.5Winner1,452.388
LMArena Text, Style ControlEntertainment, sports and media. Higher is better. No documented setup difference
Mistral Large 31,373.228
MiMo-V2.5Winner1,401.59
LMArena Text, Style ControlExcluding ties. Higher is better. No documented setup difference
Mistral Large 31,400.876
MiMo-V2.5Winner1,427.481
LMArena Text, Style ControlExpert prompts. Higher is better. No documented setup difference
Mistral Large 31,423.349
MiMo-V2.5Winner1,474.263
LMArena Text, Style ControlFrench. Higher is better. No documented setup difference
Mistral Large 31,434.923
MiMo-V2.5No clear lead1,454.676
LMArena Text, Style ControlGerman. Higher is better. No documented setup difference
Mistral Large 31,404.512
MiMo-V2.5No clear lead1,421.467
LMArena Text, Style ControlHard prompts. Higher is better. No documented setup difference
Mistral Large 31,431.026
MiMo-V2.5Winner1,461.799

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Mistral Large 3 and MiMo-V2.5
Benchmark and taskMistral Large 3MiMo-V2.5Source
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 65,336 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 44,540 anonymous pairwise votes.
1,413.556
95% confidence interval: ±3.08The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,433.798
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
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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 12,392 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,127 anonymous pairwise votes.
1,412.721
95% confidence interval: ±5.917The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,441.542
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
LMArena Text, Style ControlChinese
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,483 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,140 anonymous pairwise votes.
1,431.759
95% confidence interval: ±9.282The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,483.45
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
LMArena Text, Style ControlCoding
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 16,301 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 12,854 anonymous pairwise votes.
1,468.587
95% confidence interval: ±5.241The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,491.02
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
LMArena Text, Style ControlCreative writing
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 10,954 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 7,343 anonymous pairwise votes.
1,375.017
95% confidence interval: ±6.318The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,392.817
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
LMArena Text, Style ControlEnglish
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 27,473 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 20,213 anonymous pairwise votes.
1,426.818
95% confidence interval: ±4.282The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,452.388
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
LMArena Text, Style ControlEntertainment, sports and media
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 13,723 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 9,698 anonymous pairwise votes.
1,373.228
95% confidence interval: ±5.71The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,401.59
95% confidence interval: ±7.383The 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
LMArena Text, Style ControlExcluding ties
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 47,430 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 34,136 anonymous pairwise votes.
1,400.876
95% confidence interval: ±4.294The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,427.481
95% confidence interval: ±5.599The 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
LMArena Text, Style ControlExpert prompts
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 5,705 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 4,401 anonymous pairwise votes.
1,423.349
95% confidence interval: ±8.346The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,474.263
95% confidence interval: ±9.645The 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
LMArena Text, Style ControlFrench
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,858 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 1,754 anonymous pairwise votes.
1,434.923
95% confidence interval: ±15.523The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,454.676
95% confidence interval: ±16.333The 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
LMArena Text, Style ControlGerman
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,080 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 759 anonymous pairwise votes.
1,404.512
95% confidence interval: ±19.03The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,421.467
95% confidence interval: ±22.574The 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
LMArena Text, Style ControlHard prompts
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 39,237 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 29,811 anonymous pairwise votes.
1,431.026
95% confidence interval: ±3.848The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,461.799
95% confidence interval: ±5.088The 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
LMArena Text, Style ControlHard prompts, English
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 16,526 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 14,215 anonymous pairwise votes.
1,438.338
95% confidence interval: ±5.247The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,471.581
95% confidence interval: ±6.423The 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
LMArena Text, Style ControlInstruction following
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 20,253 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 14,987 anonymous pairwise votes.
1,399.916
95% confidence interval: ±4.811The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,431.463
95% confidence interval: ±6.27The 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
LMArena Text, Style ControlJapanese
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 661 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 513 anonymous pairwise votes.
Winner1,382.813
95% confidence interval: ±24.568The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,321.271
95% confidence interval: ±28.629The 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
LMArena Text, Style ControlKorean
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,118 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 784 anonymous pairwise votes.
1,355.204
95% confidence interval: ±19.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,373.664
95% confidence interval: ±22.433The 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
LMArena Text, Style ControlLegal and government
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,880 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 3,566 anonymous pairwise votes.
1,420.347
95% confidence interval: ±8.946The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,427.361
95% confidence interval: ±10.778The 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
LMArena Text, Style ControlLife, physical and social science
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 10,595 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 7,207 anonymous pairwise votes.
1,427.433
95% confidence interval: ±6.173The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,452.891
95% confidence interval: ±7.882The 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
LMArena Text, Style ControlLonger queries
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 23,193 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 19,717 anonymous pairwise votes.
1,416.784
95% confidence interval: ±4.746The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,452.091
95% confidence interval: ±5.953The 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
LMArena Text, Style ControlMath
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 3,755 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,327 anonymous pairwise votes.
1,402.864
95% confidence interval: ±9.902The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,440.393
95% confidence interval: ±12.473The 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
LMArena Text, Style ControlMathematical professions
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 3,175 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 2,441 anonymous pairwise votes.
1,417.813
95% confidence interval: ±10.98The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,454.25
95% confidence interval: ±12.776The 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
LMArena Text, Style ControlMedicine and healthcare
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,505 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 3,164 anonymous pairwise votes.
1,431.127
95% confidence interval: ±9.388The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,448.067
95% confidence interval: ±11.459The 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
LMArena Text, Style ControlMulti-turn
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 11,201 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 7,901 anonymous pairwise votes.
1,420.712
95% confidence interval: ±6.145The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,450.214
95% confidence interval: ±7.779The 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
LMArena Text, Style ControlNon-English
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 37,859 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 24,326 anonymous pairwise votes.
1,397.941
95% confidence interval: ±3.805The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,411.361
95% confidence interval: ±5.294The 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
LMArena Text, Style ControlPolish
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,582 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 929 anonymous pairwise votes.
1,415.726
95% confidence interval: ±15.021The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,420.076
95% confidence interval: ±19.427The 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
LMArena Text, Style ControlRussian
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 7,429 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 4,772 anonymous pairwise votes.
No clear lead1,409.803
95% confidence interval: ±7.118The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,404.83
95% confidence interval: ±9.316The 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
LMArena Text, Style ControlSoftware and IT services
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 24,350 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 18,163 anonymous pairwise votes.
1,456.163
95% confidence interval: ±4.498The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,479.843
95% confidence interval: ±5.913The 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
LMArena Text, Style ControlSpanish
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,998 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 1,414 anonymous pairwise votes.
1,406.852
95% confidence interval: ±14.343The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,411.308
95% confidence interval: ±17.191The 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
LMArena Text, Style ControlWriting, literature and language
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control
MiMo-V2.5: Snapshot: mimo-v2.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 15,693 anonymous pairwise votes.MiMo-V2.5: Style-controlled Arena rating from 10,784 anonymous pairwise votes.
1,390.534
95% confidence interval: ±5.355The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Winner1,411.069
95% confidence interval: ±6.937The 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

Related LLM comparisons

Compare Mistral Large 3 and MiMo-V2.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison