Skip to main content

Head-to-head comparison

GPT-5.4 vs. Mistral Medium 3.5

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

shared result series
56
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-5.4 and Mistral Medium 3.5
AttributeGPT-5.4Mistral Medium 3.5
ProviderOpenAIMistral AI
ReleasedMar 2026Apr 28, 2026
AvailabilityActiveActive
Model typeProprietaryOpen Weights
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,050,000 tokens256,000 tokens
Knowledge cutoffAugust 31, 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-5.4 and Mistral Medium 3.5
Price typeGPT-5.4Mistral Medium 3.5
API input$2.5 ≤272K / $5 >272K$1.5
API output$15 ≤272K / $22.5 >272K$7.5
Cache read$0.25 ≤272K / $0.5 >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-5.4Mistral Medium 3.5
API inputUSD per 1M tokens, base tier
GPT-5.4$2.5
Mistral Medium 3.5Lower price$1.5
API outputUSD per 1M tokens, base tier
GPT-5.4$15
Mistral Medium 3.5Lower price$7.5

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-5.4 and Mistral Medium 3.5
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
GPT-5.4OpenAIDirect from developerUp to 272,000 context tokens$2.5$15Source07/30/2026
OpenAIDirect from developerAbove 272,000 context tokens$5$22.5Source07/30/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-east-1$2.75$16.5Source09/07/2026
AzureVia OpenRouterazure$2.5$15Source09/07/2026
AzureVia OpenRouterazure/eu$2.75$16.5Source09/07/2026
AzureVia OpenRouterazure/us$2.75$16.5Source09/07/2026
OpenAIVia OpenRouteropenai$2.5$15Source09/07/2026
OpenAIVia OpenRouteropenai/fast$5$30Source09/07/2026
OpenAIVia OpenRouteropenai/flexLowest listed price: $1.25Lowest listed price: $7.5Source09/07/2026
Mistral Medium 3.5Mistral AIDirect from developerStandard APILowest listed price: $1.5Lowest listed price: $7.5Source07/30/2026
MistralVia OpenRoutermistralLowest listed price: $1.5Lowest listed price: $7.5Source09/07/2026
MistralVia OpenRoutermistral/eu$1.65$8.25Source09/07/2026
MistralVia OpenRoutermistral/zdrLowest listed price: $1.5Lowest listed price: $7.5Source09/07/2026

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-5.4
Mistral Medium 3.5
Coding: 100 / 97.7 (1 benchmark family)
Reasoning: 100 / 97.2 (1 benchmark family)
Mathematics: 100 / 97.9 (1 benchmark family)
Knowledge: 100 / 96.8 (1 benchmark family)
Finance: 100 / 97 (1 benchmark family)
Legal: 100 / 97.4 (1 benchmark family)
Health: 100 / 97 (1 benchmark family)
General: 100 / 97 (1 benchmark family)

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

GPT-5.4Mistral Medium 3.5
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
GPT-5.4Winner1,465.527
Mistral Medium 3.51,426.98
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,476.488
Mistral Medium 3.51,426.98
LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference
GPT-5.4Winner1,474.871
Mistral Medium 3.51,431.113
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,483.779
Mistral Medium 3.51,431.113
LMArena Text, Style ControlChinese. Higher is better. No documented setup difference
GPT-5.4Winner1,494.074
Mistral Medium 3.51,448.299
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,504.962
Mistral Medium 3.51,448.299
LMArena Text, Style ControlCoding. Higher is better. No documented setup difference
GPT-5.4Winner1,513.577
Mistral Medium 3.51,478.845
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,519.961
Mistral Medium 3.51,478.845
LMArena Text, Style ControlCreative writing. Higher is better. No documented setup difference
GPT-5.4Winner1,436.108
Mistral Medium 3.51,396.971
LMArena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,443.763
Mistral Medium 3.51,396.971
LMArena Text, Style ControlEnglish. Higher is better. No documented setup difference
GPT-5.4Winner1,468.527
Mistral Medium 3.51,444.656
LMArena Text, Style ControlEnglish. Higher is better. Test setup not documented as identical
GPT-5.4Higher measured value1,477.92
Mistral Medium 3.51,444.656

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for GPT-5.4 and Mistral Medium 3.5
Benchmark and taskGPT-5.4Mistral Medium 3.5Source
LMArena Text, Style ControlOverall
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 63,615 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,017 anonymous pairwise votes.
Winner1,465.527
95% confidence interval: ±3.807The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,426.98
95% confidence interval: ±6.556The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 60,657 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,017 anonymous pairwise votes.
Higher measured value1,476.488
95% confidence interval: ±3.881The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,426.98
95% confidence interval: ±6.556The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,060 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,148 anonymous pairwise votes.
Winner1,474.871
95% confidence interval: ±6.534The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,431.113
95% confidence interval: ±13.17The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,346 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,148 anonymous pairwise votes.
Higher measured value1,483.779
95% confidence interval: ±6.654The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,431.113
95% confidence interval: ±13.17The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,684 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 500 anonymous pairwise votes.
Winner1,494.074
95% confidence interval: ±10.702The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,448.299
95% confidence interval: ±26.61The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,482 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 500 anonymous pairwise votes.
Higher measured value1,504.962
95% confidence interval: ±10.923The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,448.299
95% confidence interval: ±26.61The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 17,704 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,079 anonymous pairwise votes.
Winner1,513.577
95% confidence interval: ±5.956The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,478.845
95% confidence interval: ±11.157The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 16,441 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,079 anonymous pairwise votes.
Higher measured value1,519.961
95% confidence interval: ±6.001The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,478.845
95% confidence interval: ±11.157The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,326 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,862 anonymous pairwise votes.
Winner1,436.108
95% confidence interval: ±7.048The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,396.971
95% confidence interval: ±14.389The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,108 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,862 anonymous pairwise votes.
Higher measured value1,443.763
95% confidence interval: ±7.189The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,396.971
95% confidence interval: ±14.389The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 29,058 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,299 anonymous pairwise votes.
Winner1,468.527
95% confidence interval: ±4.99The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,444.656
95% confidence interval: ±8.682The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 27,549 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,299 anonymous pairwise votes.
Higher measured value1,477.92
95% confidence interval: ±5.043The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,444.656
95% confidence interval: ±8.682The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 13,621 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,453 anonymous pairwise votes.
Winner1,433.464
95% confidence interval: ±6.441The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,396.875
95% confidence interval: ±12.491The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 12,946 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,453 anonymous pairwise votes.
Higher measured value1,442.467
95% confidence interval: ±6.606The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,396.875
95% confidence interval: ±12.491The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 48,871 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,299 anonymous pairwise votes.
Winner1,471.798
95% confidence interval: ±4.961The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,421.17
95% confidence interval: ±8.686The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 46,411 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,299 anonymous pairwise votes.
Higher measured value1,485.953
95% confidence interval: ±5.055The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,421.17
95% confidence interval: ±8.686The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,107 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,110 anonymous pairwise votes.
Winner1,490.311
95% confidence interval: ±8.598The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,438.278
95% confidence interval: ±17.831The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 5,765 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,110 anonymous pairwise votes.
Higher measured value1,515.538
95% confidence interval: ±8.748The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,438.278
95% confidence interval: ±17.831The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 2,327 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 438 anonymous pairwise votes.
Winner1,484.932
95% confidence interval: ±14.655The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,436.08
95% confidence interval: ±30.551The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 2,288 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 438 anonymous pairwise votes.
Higher measured value1,502.194
95% confidence interval: ±14.8The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,436.08
95% confidence interval: ±30.551The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlGerman
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 964 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 170 anonymous pairwise votes.
No clear lead1,448.071
95% confidence interval: ±20.361The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.607
95% confidence interval: ±44.317The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,056 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 170 anonymous pairwise votes.
Higher measured value1,470.385
95% confidence interval: ±19.432The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.607
95% confidence interval: ±44.317The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 41,790 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,154 anonymous pairwise votes.
Winner1,487.567
95% confidence interval: ±4.591The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,445.592
95% confidence interval: ±7.857The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 39,303 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,154 anonymous pairwise votes.
Higher measured value1,497.941
95% confidence interval: ±4.628The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,445.592
95% confidence interval: ±7.857The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 19,850 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,629 anonymous pairwise votes.
Winner1,487.46
95% confidence interval: ±5.732The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,458.246
95% confidence interval: ±10.39The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 18,552 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,629 anonymous pairwise votes.
Higher measured value1,495.34
95% confidence interval: ±5.797The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,458.246
95% confidence interval: ±10.39The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 21,742 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,561 anonymous pairwise votes.
Winner1,461.072
95% confidence interval: ±5.529The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,422.491
95% confidence interval: ±10.335The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 20,284 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,561 anonymous pairwise votes.
Higher measured value1,472.675
95% confidence interval: ±5.598The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,422.491
95% confidence interval: ±10.335The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlKorean
Test details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,132 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 178 anonymous pairwise votes.
No clear lead1,426.207
95% confidence interval: ±19.624The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,394.42
95% confidence interval: ±44.572The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,077 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 178 anonymous pairwise votes.
Higher measured value1,437.428
95% confidence interval: ±20.212The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,394.42
95% confidence interval: ±44.572The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 5,056 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 839 anonymous pairwise votes.
Winner1,476.119
95% confidence interval: ±9.309The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,437.785
95% confidence interval: ±21.302The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,896 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 839 anonymous pairwise votes.
Higher measured value1,490.489
95% confidence interval: ±9.43The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,437.785
95% confidence interval: ±21.302The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 10,310 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,823 anonymous pairwise votes.
Winner1,478.714
95% confidence interval: ±6.907The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.494
95% confidence interval: ±14.359The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 9,887 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,823 anonymous pairwise votes.
Higher measured value1,487.819
95% confidence interval: ±7.029The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.494
95% confidence interval: ±14.359The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 27,399 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,661 anonymous pairwise votes.
Winner1,478.044
95% confidence interval: ±5.365The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,430.723
95% confidence interval: ±9.428The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 26,046 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,661 anonymous pairwise votes.
Higher measured value1,483.065
95% confidence interval: ±5.438The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,430.723
95% confidence interval: ±9.428The 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,352 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 539 anonymous pairwise votes.
No clear lead1,460.556
95% confidence interval: ±10.677The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,429.582
95% confidence interval: ±24.872The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,183 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 539 anonymous pairwise votes.
Higher measured value1,493.915
95% confidence interval: ±10.961The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,429.582
95% confidence interval: ±24.872The 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,439 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 597 anonymous pairwise votes.
No clear lead1,472.767
95% confidence interval: ±10.952The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.192
95% confidence interval: ±23.932The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 3,248 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 597 anonymous pairwise votes.
Higher measured value1,499.328
95% confidence interval: ±11.167The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,442.192
95% confidence interval: ±23.932The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,674 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 802 anonymous pairwise votes.
Winner1,467.247
95% confidence interval: ±9.706The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,423.47
95% confidence interval: ±21.791The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 4,468 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 802 anonymous pairwise votes.
Higher measured value1,475.67
95% confidence interval: ±9.928The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,423.47
95% confidence interval: ±21.791The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 11,973 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,803 anonymous pairwise votes.
Winner1,480.329
95% confidence interval: ±6.718The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,431.302
95% confidence interval: ±14.433The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlMulti-turn
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 11,276 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,803 anonymous pairwise votes.
Higher measured value1,493.597
95% confidence interval: ±6.791The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,431.302
95% confidence interval: ±14.433The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.		LMArena
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlNon-English
Test details
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 34,555 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,718 anonymous pairwise votes.
Winner1,457.74
95% confidence interval: ±4.704The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,406.687
95% confidence interval: ±8.36The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 33,108 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,718 anonymous pairwise votes.
Higher measured value1,468.508
95% confidence interval: ±4.748The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,406.687
95% confidence interval: ±8.36The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,256 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 226 anonymous pairwise votes.
Winner1,471.649
95% confidence interval: ±17.194The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,407.955
95% confidence interval: ±38.858The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,297 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 226 anonymous pairwise votes.
Higher measured value1,481.999
95% confidence interval: ±17.11The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,407.955
95% confidence interval: ±38.858The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,931 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,143 anonymous pairwise votes.
Winner1,470.588
95% confidence interval: ±8.018The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,415.692
95% confidence interval: ±17.832The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 6,518 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,143 anonymous pairwise votes.
Higher measured value1,489.834
95% confidence interval: ±8.237The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,415.692
95% confidence interval: ±17.832The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 25,295 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,320 anonymous pairwise votes.
Winner1,499.006
95% confidence interval: ±5.265The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,470.76
95% confidence interval: ±9.541The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 23,828 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,320 anonymous pairwise votes.
Higher measured value1,506.521
95% confidence interval: ±5.304The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,470.76
95% confidence interval: ±9.541The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 1,989 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 377 anonymous pairwise votes.
Winner1,460.91
95% confidence interval: ±14.754The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,386.845
95% confidence interval: ±32.418The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 2,023 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 377 anonymous pairwise votes.
Higher measured value1,457.508
95% confidence interval: ±14.616The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,386.845
95% confidence interval: ±32.418The 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-5.4: Snapshot: gpt-5.4, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 15,387 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,734 anonymous pairwise votes.
Winner1,459.652
95% confidence interval: ±6.094The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,405.944
95% confidence interval: ±11.74The 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-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena text, style control
Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlGPT-5.4: Style-controlled Arena rating from 15,037 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,734 anonymous pairwise votes.
Higher measured value1,465.575
95% confidence interval: ±6.138The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,405.944
95% confidence interval: ±11.74The 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-5.4 and Mistral Medium 3.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison