Skip to main content

Head-to-head comparison

GPT-5.5 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
58
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 GPT-5.5 and Mistral Large 3
AttributeGPT-5.5Mistral Large 3
ProviderOpenAIMistral AI
ReleasedApr 2026Dec 2, 2025
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot published675B, 41B active
ArchitectureNot publishedMixture of Experts
Context window1,050,000 tokens256,000 tokens
Knowledge cutoffDecember 1, 2025Not 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 GPT-5.5 and Mistral Large 3
Price typeGPT-5.5Mistral Large 3
API input$5 ≤272K / $10 >272K$0.5
API output$30 ≤272K / $45 >272K$1.5
Cache read$0.5 ≤272K / $1 >272KNot listed
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source07/30/2026 Source
GPT-5.5Mistral Large 3
API inputUSD per 1M tokens, base tier
GPT-5.5$5
Mistral Large 3Lower price$0.5
API outputUSD per 1M tokens, base tier
GPT-5.5$30
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 GPT-5.5 and Mistral Large 3
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.5OpenAIDirect from developerUp to 272,000 context tokens$5$30Source07/30/2026
OpenAIDirect from developerAbove 272,000 context tokens$10$45Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$5.5$33Source09/07/2026
AzureVia OpenRouterazure$5$30Source09/07/2026
AzureVia OpenRouterazure/eu$5.5$33Source09/07/2026
AzureVia OpenRouterazure/us$5.5$33Source09/07/2026
OpenAIVia OpenRouteropenai$5$30Source09/07/2026
OpenAIVia OpenRouteropenai/fast$12.5$75Source09/07/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $2.5Lowest listed price: $15Source09/07/2026
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
GPT-5.5
Mistral Large 3
Coding: 100 / 97.3 (1 benchmark family)
Reasoning: 100 / 95.2 (1 benchmark family)
Mathematics: 100 / 94 (1 benchmark family)
Knowledge: 100 / 95.4 (1 benchmark family)
Finance: 100 / 95.1 (1 benchmark family)
Legal: 100 / 95.6 (1 benchmark family)
Health: 100 / 96.3 (1 benchmark family)
General: 100 / 95.2 (1 benchmark family)

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

GPT-5.5Mistral Large 3
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.5Winner1,477.235
Mistral Large 31,413.556
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,482.334
Mistral Large 31,413.556
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
GPT-5.5Winner1,485.915
Mistral Large 31,412.721
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,489.993
Mistral Large 31,412.721
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
GPT-5.5Winner1,530.095
Mistral Large 31,431.759
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,515.679
Mistral Large 31,431.759
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
GPT-5.5Winner1,508.939
Mistral Large 31,468.587
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,520.129
Mistral Large 31,468.587
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
GPT-5.5Winner1,448.376
Mistral Large 31,375.017
LMArena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,452.482
Mistral Large 31,375.017
LMArena Text, Style ControlEnglish. Higher is better. No documented setup difference
GPT-5.5Winner1,482.081
Mistral Large 31,426.818
LMArena Text, Style ControlEnglish. Higher is better. Test setup not documented as identical
GPT-5.5Higher measured value1,484.772
Mistral Large 31,426.818

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.5 and Mistral Large 3
Benchmark and taskGPT-5.5Mistral 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 64,686 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 65,336 anonymous pairwise votes.
Winner1,477.235
95% confidence interval: ±3.839The 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 ControlOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 63,265 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 65,336 anonymous pairwise votes.
Higher measured value1,482.334
95% confidence interval: ±3.856The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 12,904 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 12,392 anonymous pairwise votes.
Winner1,485.915
95% confidence interval: ±6.577The 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 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-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 12,594 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 12,392 anonymous pairwise votes.
Higher measured value1,489.993
95% confidence interval: ±6.59The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,552 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,483 anonymous pairwise votes.
Winner1,530.095
95% confidence interval: ±11.053The 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 ControlChinese
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,648 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,483 anonymous pairwise votes.
Higher measured value1,515.679
95% confidence interval: ±10.674The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 18,325 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,301 anonymous pairwise votes.
Winner1,508.939
95% confidence interval: ±5.848The 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 ControlCoding
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 17,606 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,301 anonymous pairwise votes.
Higher measured value1,520.129
95% confidence interval: ±5.918The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 11,878 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,954 anonymous pairwise votes.
Winner1,448.376
95% confidence interval: ±6.88The 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 ControlCreative writing
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 11,556 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,954 anonymous pairwise votes.
Higher measured value1,452.482
95% confidence interval: ±6.902The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 29,547 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 27,473 anonymous pairwise votes.
Winner1,482.081
95% confidence interval: ±4.938The 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 ControlEnglish
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 28,840 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 27,473 anonymous pairwise votes.
Higher measured value1,484.772
95% confidence interval: ±4.944The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 15,289 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,723 anonymous pairwise votes.
Winner1,446.376
95% confidence interval: ±6.282The 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 ControlEntertainment, sports and media
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 14,828 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,723 anonymous pairwise votes.
Higher measured value1,450.494
95% confidence interval: ±6.344The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 49,327 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 47,430 anonymous pairwise votes.
Winner1,486.307
95% confidence interval: ±5.005The 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 ControlExcluding ties
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 47,980 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 47,430 anonymous pairwise votes.
Higher measured value1,493.228
95% confidence interval: ±5.003The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 6,796 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,705 anonymous pairwise votes.
Winner1,511.055
95% confidence interval: ±8.262The 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 ControlExpert prompts
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 6,546 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,705 anonymous pairwise votes.
Higher measured value1,513.567
95% confidence interval: ±8.306The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 2,369 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,858 anonymous pairwise votes.
Winner1,501.604
95% confidence interval: ±14.559The 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 ControlFrench
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 2,328 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,858 anonymous pairwise votes.
Higher measured value1,494.639
95% confidence interval: ±14.565The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,012 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,080 anonymous pairwise votes.
Winner1,491.677
95% confidence interval: ±20.229The 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 ControlGerman
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 974 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,080 anonymous pairwise votes.
Higher measured value1,473.396
95% confidence interval: ±20.184The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 42,992 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 39,237 anonymous pairwise votes.
Winner1,498.125
95% confidence interval: ±4.517The 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
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 41,441 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 39,237 anonymous pairwise votes.
Higher measured value1,501.683
95% confidence interval: ±4.543The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 20,195 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,526 anonymous pairwise votes.
Winner1,498.824
95% confidence interval: ±5.695The 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 ControlHard prompts, English
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 19,465 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,526 anonymous pairwise votes.
Higher measured value1,499.763
95% confidence interval: ±5.725The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 22,401 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 20,253 anonymous pairwise votes.
Winner1,473.969
95% confidence interval: ±5.476The 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 ControlInstruction following
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 21,691 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 20,253 anonymous pairwise votes.
Higher measured value1,478.507
95% confidence interval: ±5.531The 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 setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 723 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 661 anonymous pairwise votes.
Winner1,484.154
95% confidence interval: ±24.445The 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 ControlJapanese
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 799 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 661 anonymous pairwise votes.
Higher measured value1,505.889
95% confidence interval: ±23.164The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,094 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,118 anonymous pairwise votes.
Winner1,427.974
95% confidence interval: ±19.644The 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 ControlKorean
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,090 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,118 anonymous pairwise votes.
Higher measured value1,446.278
95% confidence interval: ±19.47The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 5,331 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,880 anonymous pairwise votes.
Winner1,485.929
95% confidence interval: ±9.075The 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 ControlLegal and government
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 5,130 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,880 anonymous pairwise votes.
Higher measured value1,495.297
95% confidence interval: ±9.236The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 10,700 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,595 anonymous pairwise votes.
Winner1,495.773
95% confidence interval: ±6.831The 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 ControlLife, physical and social science
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 10,554 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 10,595 anonymous pairwise votes.
Higher measured value1,498.539
95% confidence interval: ±6.867The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 29,781 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 23,193 anonymous pairwise votes.
Winner1,484.838
95% confidence interval: ±5.2The 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 ControlLonger queries
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 28,638 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 23,193 anonymous pairwise votes.
Higher measured value1,488.354
95% confidence interval: ±5.257The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,230 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,755 anonymous pairwise votes.
Winner1,501.81
95% confidence interval: ±11.02The 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 ControlMath
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,161 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,755 anonymous pairwise votes.
Higher measured value1,490.657
95% confidence interval: ±10.928The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,601 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,175 anonymous pairwise votes.
Winner1,500.216
95% confidence interval: ±10.861The 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 ControlMathematical professions
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 3,535 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 3,175 anonymous pairwise votes.
Higher measured value1,505.572
95% confidence interval: ±10.806The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 4,840 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,505 anonymous pairwise votes.
Winner1,485.8
95% confidence interval: ±9.564The 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 ControlMedicine and healthcare
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 4,726 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,505 anonymous pairwise votes.
Higher measured value1,477.659
95% confidence interval: ±9.561The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 11,272 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,201 anonymous pairwise votes.
Winner1,482.216
95% confidence interval: ±6.865The 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 ControlMulti-turn
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 10,902 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 11,201 anonymous pairwise votes.
Higher measured value1,490.033
95% confidence interval: ±6.973The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 35,138 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 37,859 anonymous pairwise votes.
Winner1,466.636
95% confidence interval: ±4.653The 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 ControlNon-English
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 34,424 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 37,859 anonymous pairwise votes.
Higher measured value1,474.665
95% confidence interval: ±4.693The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,133 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,582 anonymous pairwise votes.
Winner1,470.019
95% confidence interval: ±18.213The 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 ControlPolish
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,091 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,582 anonymous pairwise votes.
Higher measured value1,479.14
95% confidence interval: ±18.375The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 6,486 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 7,429 anonymous pairwise votes.
Winner1,479.174
95% confidence interval: ±8.197The 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 ControlRussian
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 6,457 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 7,429 anonymous pairwise votes.
Higher measured value1,484.259
95% confidence interval: ±8.185The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 25,850 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 24,350 anonymous pairwise votes.
Winner1,504.177
95% confidence interval: ±5.202The 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 ControlSoftware and IT services
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 25,147 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 24,350 anonymous pairwise votes.
Higher measured value1,510.903
95% confidence interval: ±5.208The 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 setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,953 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,998 anonymous pairwise votes.
Winner1,462.461
95% confidence interval: ±14.956The 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 ControlSpanish
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 1,837 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,998 anonymous pairwise votes.
Higher measured value1,467.712
95% confidence interval: ±15.152The 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 betterGPT-5.5: Snapshot: gpt-5.5, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 16,528 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 15,693 anonymous pairwise votes.
Winner1,465.967
95% confidence interval: ±6.056The 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
LMArena Text, Style ControlWriting, literature and language
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.5: Snapshot: gpt-5.5-high, Reasoning: high, Harness: Arena text, style control
Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGPT-5.5: Style-controlled Arena rating from 16,173 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 15,693 anonymous pairwise votes.
Higher measured value1,472.012
95% confidence interval: ±6.081The 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 GPT-5.5 and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison