Head-to-head comparison

Mistral Large 3 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: 28
distinct benchmarks: 1
latest retrieval: 2026-09-04

First modelSecond model

Specifications

General specifications

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

Specifications for Mistral Large 3 and Mistral Medium 3.5
Attribute	Mistral Large 3	Mistral Medium 3.5
Provider	Mistral AI	Mistral AI
Released	Dec 2, 2025	Apr 28, 2026
Availability	Active	Active
Model type	Open Weights	Open Weights
Parameters	675B, 41B active	128B
Architecture	Mixture of Experts	Dense
Context window	262,144 tokens	262,144 tokens
Knowledge cutoff	Not published	Not published
Technical sources	Model, Context	Model, Context

Pricing

API pricing compared

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

API pricing for Mistral Large 3 and Mistral Medium 3.5
Price type	Mistral Large 3	Mistral Medium 3.5
API input	$0.5	$1.5
API output	$1.5	$7.5
Cache read	Not listed	Not listed
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	07/30/2026 Source	07/30/2026 Source

Mistral Large 3Mistral Medium 3.5

API inputUSD per 1M tokens, base tier

Mistral Large 3$0.5

Mistral Medium 3.5$1.5

API outputUSD per 1M tokens, base tier

Mistral Large 3$1.5

Mistral Medium 3.5$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 Mistral Large 3 and Mistral Medium 3.5
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Mistral Large 3	Mistral AI	Direct from developerStandard API	Lowest listed price: $0.5	Lowest listed price: $1.5	Source07/30/2026
	Mistral	Via OpenRoutermistral	Lowest listed price: $0.5	Lowest listed price: $1.5	Source09/08/2026
	Mistral	Via OpenRoutermistral/eu	$0.55	$1.65	Source09/08/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source09/08/2026
Mistral Medium 3.5	Mistral AI	Direct from developerStandard API	Lowest listed price: $1.5	Lowest listed price: $7.5	Source07/30/2026
	Mistral	Via OpenRoutermistral	Lowest listed price: $1.5	Lowest listed price: $7.5	Source09/08/2026
	Mistral	Via OpenRoutermistral/eu	$1.65	$8.25	Source09/08/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $1.5	Lowest listed price: $7.5	Source09/08/2026

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.

Mistral Large 3

Mistral Medium 3.5

Coding: 99.3 / 100 (1 benchmark family)

Reasoning: 98.9 / 100 (1 benchmark family)

Mathematics: 98.2 / 100 (1 benchmark family)

Knowledge: 99 / 100 (1 benchmark family)

Finance: 98.7 / 100 (1 benchmark family)

Legal: 98.8 / 100 (1 benchmark family)

Health: 100 / 99.5 (1 benchmark family)

General: 98.9 / 99.9 (1 benchmark family)

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

Mistral Large 3Mistral Medium 3.5

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

Mistral Large 31,413.556

Mistral Medium 3.51,426.98

LMArena Text, Style ControlBusiness, management and finance. Higher is better. No documented setup difference

Mistral Large 31,412.721

Mistral Medium 3.51,431.113

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

Mistral Large 31,431.759

Mistral Medium 3.51,448.299

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

Mistral Large 31,468.587

Mistral Medium 3.51,478.845

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

Mistral Large 31,375.017

Mistral Medium 3.51,396.971

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

Mistral Large 31,426.818

Mistral Medium 3.51,444.656

LMArena Text, Style ControlEntertainment, sports and media. Higher is better. No documented setup difference

Mistral Large 31,373.228

Mistral Medium 3.51,396.875

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

Mistral Large 31,400.876

Mistral Medium 3.51,421.17

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

Mistral Large 31,423.349

Mistral Medium 3.51,438.278

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

Mistral Large 31,434.923

Mistral Medium 3.51,436.08

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

Mistral Large 31,404.512

Mistral Medium 3.51,442.607

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

Mistral Large 31,431.026

Mistral Medium 3.51,445.592

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Mistral Large 3

API access was unavailable for this run. The model was not evaluated.

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: mistralai/mistral-large-2512
Pinned endpoint: Mistral | mistralai/mistral-large-2512
Reasoning setting: none
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Mistral Medium 3.5

API access was unavailable for this run. The model was not evaluated.

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: mistralai/mistral-medium-3-5
Pinned endpoint: Mistral | mistralai/mistral-medium-3.5-20260430
Reasoning setting: high
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

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

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

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

More matchups

Compare Mistral Large 3 and Mistral Medium 3.5 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Benchmark scores for Mistral Large 3 and Mistral Medium 3.5
Benchmark and task	Mistral Large 3	Mistral Medium 3.5	Source
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 65,336 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,017 anonymous pairwise votes.	1,413.556 95% confidence interval: ±3.08The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,426.98 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 12,392 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,148 anonymous pairwise votes.	1,412.721 95% confidence interval: ±5.917The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,431.113 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,483 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 500 anonymous pairwise votes.	1,431.759 95% confidence interval: ±9.282The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,448.299 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 16,301 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,079 anonymous pairwise votes.	1,468.587 95% confidence interval: ±5.241The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,478.845 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 10,954 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,862 anonymous pairwise votes.	1,375.017 95% confidence interval: ±6.318The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,396.971 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 27,473 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,299 anonymous pairwise votes.	1,426.818 95% confidence interval: ±4.282The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,444.656 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 13,723 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,453 anonymous pairwise votes.	1,373.228 95% confidence interval: ±5.71The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,396.875 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 47,430 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,299 anonymous pairwise votes.	1,400.876 95% confidence interval: ±4.294The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,421.17 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 5,705 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,110 anonymous pairwise votes.	1,423.349 95% confidence interval: ±8.346The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,438.278 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,858 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 438 anonymous pairwise votes.	1,434.923 95% confidence interval: ±15.523The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,436.08 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,080 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 170 anonymous pairwise votes.	1,404.512 95% confidence interval: ±19.03The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,442.607 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 39,237 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,154 anonymous pairwise votes.	1,431.026 95% confidence interval: ±3.848The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,445.592 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 16,526 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,629 anonymous pairwise votes.	1,438.338 95% confidence interval: ±5.247The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,458.246 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 20,253 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,561 anonymous pairwise votes.	1,399.916 95% confidence interval: ±4.811The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,422.491 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,118 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 178 anonymous pairwise votes.	1,355.204 95% confidence interval: ±19.178The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,394.42 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,880 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 839 anonymous pairwise votes.	1,420.347 95% confidence interval: ±8.946The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,437.785 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 10,595 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,823 anonymous pairwise votes.	1,427.433 95% confidence interval: ±6.173The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,433.494 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 23,193 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,661 anonymous pairwise votes.	1,416.784 95% confidence interval: ±4.746The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,430.723 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 3,755 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 539 anonymous pairwise votes.	1,402.864 95% confidence interval: ±9.902The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,429.582 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 3,175 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 597 anonymous pairwise votes.	1,417.813 95% confidence interval: ±10.98The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,442.192 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 4,505 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 802 anonymous pairwise votes.	No clear lead1,431.127 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.	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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 11,201 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,803 anonymous pairwise votes.	1,420.712 95% confidence interval: ±6.145The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,431.302 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 37,859 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,718 anonymous pairwise votes.	1,397.941 95% confidence interval: ±3.805The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,406.687 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,582 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 226 anonymous pairwise votes.	No clear lead1,415.726 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.	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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 7,429 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,143 anonymous pairwise votes.	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.	No clear lead1,415.692 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 betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 24,350 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,320 anonymous pairwise votes.	1,456.163 95% confidence interval: ±4.498The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,470.76 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 1,998 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 377 anonymous pairwise votes.	No clear lead1,406.852 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.	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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 15,693 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,734 anonymous pairwise votes.	1,390.534 95% confidence interval: ±5.355The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,405.944 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