Skip to main content

Head-to-head comparison

Gemini 3.5 Flash-Lite vs. Mistral Large 3

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 Gemini 3.5 Flash-Lite and Mistral Large 3
AttributeGemini 3.5 Flash-LiteMistral Large 3
ProviderGoogleMistral AI
ReleasedJul 21, 2026Dec 2, 2025
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot published675B, 41B active
ArchitectureNot publishedMixture of Experts
Context window1,048,576 tokens256,000 tokens
Knowledge cutoffNot publishedNot published
Technical sourcesModelModel

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 Gemini 3.5 Flash-Lite and Mistral Large 3
Price typeGemini 3.5 Flash-LiteMistral Large 3
API input$0.3$0.5
API output$2.5$1.5
Cache read$0.03Not listed
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source07/30/2026 Source
Gemini 3.5 Flash-LiteMistral Large 3
API inputUSD per 1M tokens, base tier
Gemini 3.5 Flash-LiteLower price$0.3
Mistral Large 3$0.5
API outputUSD per 1M tokens, base tier
Gemini 3.5 Flash-Lite$2.5
Mistral Large 3Lower price$1.5

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 Gemini 3.5 Flash-Lite and Mistral Large 3
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Gemini 3.5 Flash-LiteGoogleDirect from developerStandard API$0.3$2.5Source07/30/2026
GoogleVia OpenRoutergoogle-vertex/eu$0.33$2.75Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/global$0.3$2.5Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/global/flexLowest listed price: $0.15Lowest listed price: $1.25Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/global/priority$0.54$4.5Source09/07/2026
GoogleVia OpenRoutergoogle-vertex/us$0.33$2.75Source09/07/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$0.3$2.5Source09/07/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $0.15Lowest listed price: $1.25Source09/07/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$0.54$4.5Source09/07/2026
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

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
Gemini 3.5 Flash-Lite
Mistral Large 3
Coding: 100 / 97.7 (1 benchmark family)
Reasoning: 100 / 97.1 (1 benchmark family)
Mathematics: 100 / 97.7 (1 benchmark family)
Knowledge: 100 / 96.8 (1 benchmark family)
Finance: 100 / 96.8 (1 benchmark family)
Legal: 100 / 97.4 (1 benchmark family)
Health: 100 / 97.1 (1 benchmark family)
General: 100 / 96.5 (1 benchmark family)

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

Gemini 3.5 Flash-LiteMistral Large 3
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,456.812
Mistral Large 31,413.556
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,459.944
Mistral Large 31,412.721
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,483.996
Mistral Large 31,431.759
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,503.03
Mistral Large 31,468.587
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,436.233
Mistral Large 31,375.017
LMArena Text, Style ControlEnglish. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,460.361
Mistral Large 31,426.818
LMArena Text, Style ControlEntertainment, sports and media. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,432.812
Mistral Large 31,373.228
LMArena Text, Style ControlExcluding ties. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,461.45
Mistral Large 31,400.876
LMArena Text, Style ControlExpert prompts. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,467.501
Mistral Large 31,423.349
LMArena Text, Style ControlFrench. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,486.448
Mistral Large 31,434.923
LMArena Text, Style ControlGerman. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,464.641
Mistral Large 31,404.512
LMArena Text, Style ControlHard prompts. Higher is better. No documented setup difference
Gemini 3.5 Flash-LiteWinner1,475.158
Mistral Large 31,431.026

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.5 Flash-Lite and Mistral Large 3
Benchmark and taskGemini 3.5 Flash-LiteMistral Large 3Source
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 21,843 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 65,336 anonymous pairwise votes.
Winner1,456.812
95% confidence interval: ±5.216The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 4,096 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 12,392 anonymous pairwise votes.
Winner1,459.944
95% confidence interval: ±9.744The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 1,535 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,483 anonymous pairwise votes.
Winner1,483.996
95% confidence interval: ±15.959The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 6,146 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,301 anonymous pairwise votes.
Winner1,503.03
95% confidence interval: ±8.334The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 4,491 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,954 anonymous pairwise votes.
Winner1,436.233
95% confidence interval: ±9.77The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 9,090 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 27,473 anonymous pairwise votes.
Winner1,460.361
95% confidence interval: ±7.047The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 5,663 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,723 anonymous pairwise votes.
Winner1,432.812
95% confidence interval: ±8.825The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 16,468 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 47,430 anonymous pairwise votes.
Winner1,461.45
95% confidence interval: ±6.788The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 2,471 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,705 anonymous pairwise votes.
Winner1,467.501
95% confidence interval: ±12.303The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlFrench
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 729 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,858 anonymous pairwise votes.
Winner1,486.448
95% confidence interval: ±22.982The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlGerman
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 406 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,080 anonymous pairwise votes.
Winner1,464.641
95% confidence interval: ±29.398The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 14,613 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 39,237 anonymous pairwise votes.
Winner1,475.158
95% confidence interval: ±6.151The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 6,015 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,526 anonymous pairwise votes.
Winner1,476.524
95% confidence interval: ±8.355The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 7,798 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 20,253 anonymous pairwise votes.
Winner1,441.972
95% confidence interval: ±7.591The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlJapanese
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 347 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 661 anonymous pairwise votes.
No clear lead1,439.157
95% confidence interval: ±33.045The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,382.813
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlKorean
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 427 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,118 anonymous pairwise votes.
Winner1,419.225
95% confidence interval: ±28.759The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlLegal and government
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 1,846 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,880 anonymous pairwise votes.
Winner1,458.775
95% confidence interval: ±14.333The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 3,594 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,595 anonymous pairwise votes.
Winner1,482.587
95% confidence interval: ±10.263The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 10,464 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 23,193 anonymous pairwise votes.
Winner1,463.09
95% confidence interval: ±7.088The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 943 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,755 anonymous pairwise votes.
Winner1,438.543
95% confidence interval: ±19.104The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 1,160 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,175 anonymous pairwise votes.
Winner1,449.744
95% confidence interval: ±17.619The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlMedicine and healthcare
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 1,599 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,505 anonymous pairwise votes.
Winner1,474.225
95% confidence interval: ±15.438The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 3,662 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,201 anonymous pairwise votes.
Winner1,465.285
95% confidence interval: ±10.462The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 12,751 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 37,859 anonymous pairwise votes.
Winner1,448.561
95% confidence interval: ±6.331The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlPolish
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 315 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,582 anonymous pairwise votes.
Winner1,467.003
95% confidence interval: ±32.378The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlRussian
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 2,179 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 7,429 anonymous pairwise votes.
Winner1,466.843
95% confidence interval: ±13.064The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,409.803
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 8,836 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 24,350 anonymous pairwise votes.
Winner1,491.402
95% confidence interval: ±7.204The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 554 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,998 anonymous pairwise votes.
No clear lead1,441.291
95% confidence interval: ±25.992The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 betterGemini 3.5 Flash-Lite: Snapshot: gemini-3.5-flash-lite, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGemini 3.5 Flash-Lite: Style-controlled Arena rating from 5,853 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 15,693 anonymous pairwise votes.
Winner1,444.31
95% confidence interval: ±8.642The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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.		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 Gemini 3.5 Flash-Lite and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison