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: 36
distinct benchmarks: 9
latest retrieval: 2026-09-29

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	09/22/2026 Source	09/22/2026 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	Source09/22/2026
	Mistral	Via OpenRoutermistral/eu	$0.55	$1.65	Source10/02/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source10/02/2026
Mistral Medium 3.5	Mistral AI	Direct from developerStandard API	Lowest listed price: $1.5	Lowest listed price: $7.5	Source09/22/2026
	Mistral	Via OpenRoutermistral	Lowest listed price: $1.5	Lowest listed price: $7.5	Source10/02/2026
	Mistral	Via OpenRoutermistral/eu	$1.65	$8.25	Source10/02/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $1.5	Lowest listed price: $7.5	Source10/02/2026

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: 80.9 / 100 (2 benchmark families)

Reasoning: 99.6 / 75.5 (2 benchmark families)

Mathematics: 98.2 / 100 (1 benchmark family)

Knowledge: 99.6 / 97.2 (2 benchmark families)

Finance: 99.6 / 86.2 (4 benchmark families)

Legal: 98.9 / 100 (1 benchmark family)

Agentic tasks: 29.6 / 100 (1 benchmark family)

Health: 100 / 99.4 (1 benchmark family)

36 matched rows from 9 benchmark families were considered. The radar shows 8 of 10 comparable categories.

Mistral Large 3Mistral Medium 3.5

CorpFin v2Overall. Higher is better. No documented setup difference

Mistral Large 361.033 %

Mistral Medium 3.558.78 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Mistral Large 368.434 %

Mistral Medium 3.534.848 %

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

Mistral Large 31,413.254

Mistral Medium 3.51,426.128

MMLU-ProOverall. Higher is better. No documented setup difference

Mistral Large 379.823 %

Mistral Medium 3.575.335 %

MortgageTaxOverall. Higher is better. No documented setup difference

Mistral Large 352.106 %

Mistral Medium 3.528.895 %

SAGEOverall. Higher is better. No documented setup difference

Mistral Large 324.595 %

Mistral Medium 3.537.613 %

SWE-bench VerifiedOverall. Higher is better. No documented setup difference

Mistral Large 341.4 %

Mistral Medium 3.566.4 %

TaxEval v2Overall. Higher is better. No documented setup difference

Mistral Large 373.058 %

Mistral Medium 3.567.988 %

Terminal-Bench 2.0Overall. Higher is better. No documented setup difference

Mistral Large 38.989 %

Mistral Medium 3.530.337 %

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

Mistral Large 31,409.446

Mistral Medium 3.51,430.173

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

Mistral Large 31,434.058

Mistral Medium 3.51,446.524

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

Mistral Large 31,469.182

Mistral Medium 3.51,477.898

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

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.

Reasoning (model default): no reasoning mode Source

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: mistralai/mistral-large-2512
Reasoning setting: not specified
Pinned endpoint: Mistral | mistralai/mistral-large-2512
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.

Reasoning (requested): high

First attempt

Run date: 7 Sept 2026
API provider: openrouter
Requested API model: mistralai/mistral-medium-3-5
Reasoning setting: high
Pinned endpoint: Mistral | mistralai/mistral-medium-3.5-20260430
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
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner61.033 %	58.78 %	Vals AI Source details Data as of: 08/12/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner68.434 %	34.848 %	Vals AI Source details Data as of: 09/01/2026
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 77,456 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 11,693 anonymous pairwise votes.	1,413.254 95% confidence interval: ±2.912The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,426.128 95% confidence interval: ±6.42The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/25/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner79.823 %	75.335 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner52.106 %	28.895 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	24.595 %	Winner37.613 %	Vals AI Source details Data as of: 09/26/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	41.4 %	Winner66.4 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner73.058 %	67.988 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details No documented difference in the test setupVersion: 2.0Metric: accuracyScoring: Higher is better	8.989 %	Winner30.337 %	Vals AI Source details Data as of: 06/04/2026
LMArena Text, Style ControlBusiness, management and finance Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterMistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style control Mistral Medium 3.5: Snapshot: mistral-medium-3.5, Harness: Arena text, style controlMistral Large 3: Style-controlled Arena rating from 14,597 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,256 anonymous pairwise votes.	1,409.446 95% confidence interval: ±5.509The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,430.173 95% confidence interval: ±12.827The 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: 09/25/2026
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 5,845 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 621 anonymous pairwise votes.	1,434.058 95% confidence interval: ±8.22The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,446.524 95% confidence interval: ±23.931The 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: 09/25/2026
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 19,574 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,282 anonymous pairwise votes.	1,469.182 95% confidence interval: ±4.902The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,477.898 95% confidence interval: ±10.854The 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: 09/25/2026
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 13,448 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,999 anonymous pairwise votes.	1,372.648 95% confidence interval: ±5.824The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,397.828 95% confidence interval: ±13.94The 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: 09/25/2026
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 32,060 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,562 anonymous pairwise votes.	1,426.615 95% confidence interval: ±4.05The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,442.84 95% confidence interval: ±8.53The 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: 09/25/2026
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 16,716 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,618 anonymous pairwise votes.	1,371.316 95% confidence interval: ±5.299The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,394.24 95% confidence interval: ±12.151The 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: 09/25/2026
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 56,501 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 8,856 anonymous pairwise votes.	1,400.18 95% confidence interval: ±4.058The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,419.562 95% confidence interval: ±8.482The 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: 09/25/2026
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 7,295 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,205 anonymous pairwise votes.	1,427.543 95% confidence interval: ±7.482The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,433.7 95% confidence interval: ±17.235The 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: 09/25/2026
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 2,181 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 453 anonymous pairwise votes.	1,432.389 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.	No clear lead1,435.855 95% confidence interval: ±29.943The 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: 09/25/2026
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 1,257 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 173 anonymous pairwise votes.	1,409.467 95% confidence interval: ±17.833The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,447.96 95% confidence interval: ±43.885The 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: 09/25/2026
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 47,316 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 7,627 anonymous pairwise votes.	1,431.274 95% confidence interval: ±3.63The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,444.677 95% confidence interval: ±7.686The 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: 09/25/2026
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 19,638 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,821 anonymous pairwise votes.	1,439.274 95% confidence interval: ±4.91The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,455.806 95% confidence interval: ±10.148The 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: 09/25/2026
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 24,861 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 3,827 anonymous pairwise votes.	1,400.115 95% confidence interval: ±4.491The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	Winner1,420.763 95% confidence interval: ±10.011The 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: 09/25/2026
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 1,318 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 188 anonymous pairwise votes.	1,356.821 95% confidence interval: ±17.794The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,392.677 95% confidence interval: ±43.291The 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: 09/25/2026
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 5,879 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 893 anonymous pairwise votes.	1,421.357 95% confidence interval: ±8.211The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,437.755 95% confidence interval: ±20.721The 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: 09/25/2026
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 12,690 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,939 anonymous pairwise votes.	1,428.685 95% confidence interval: ±5.734The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,435.825 95% confidence interval: ±13.971The 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: 09/25/2026
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 29,146 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 5,065 anonymous pairwise votes.	1,417.29 95% confidence interval: ±4.417The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,428.117 95% confidence interval: ±9.119The 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: 09/25/2026
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 4,411 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 565 anonymous pairwise votes.	1,401.493 95% confidence interval: ±9.177The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,428.606 95% confidence interval: ±24.143The 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: 09/25/2026
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 4,047 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 653 anonymous pairwise votes.	1,413.935 95% confidence interval: ±9.781The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,438.481 95% confidence interval: ±22.896The 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: 09/25/2026
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 5,443 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 844 anonymous pairwise votes.	No clear lead1,430.076 95% confidence interval: ±8.59The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,421.161 95% confidence interval: ±21.257The 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: 09/25/2026
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 13,164 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,925 anonymous pairwise votes.	1,419.382 95% confidence interval: ±5.74The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,432.256 95% confidence interval: ±14.007The 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: 09/25/2026
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 45,384 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 6,131 anonymous pairwise votes.	1,397.089 95% confidence interval: ±3.587The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,406.139 95% confidence interval: ±8.159The 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: 09/25/2026
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 1,754 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 235 anonymous pairwise votes.	1,414.116 95% confidence interval: ±14.298The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,415.979 95% confidence interval: ±38.135The 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: 09/25/2026
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 9,292 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 1,242 anonymous pairwise votes.	1,408.043 95% confidence interval: ±6.505The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,410.34 95% confidence interval: ±17.157The 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: 09/25/2026
LMArena Text, Style ControlSoftware and IT services 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 29,068 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 4,587 anonymous pairwise votes.	1,455.584 95% confidence interval: ±4.237The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,468.806 95% confidence interval: ±9.304The 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: 09/25/2026
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 2,328 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 393 anonymous pairwise votes.	No clear lead1,405.285 95% confidence interval: ±13.338The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,392.394 95% confidence interval: ±31.573The 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: 09/25/2026
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 19,002 anonymous pairwise votes.Mistral Medium 3.5: Style-controlled Arena rating from 2,919 anonymous pairwise votes.	1,388.294 95% confidence interval: ±4.988The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,403.766 95% confidence interval: ±11.409The 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: 09/25/2026
Key to the marks:better valuebetter, but not conclusivetie