Head-to-head comparison

Grok 4.5 vs. Mistral Large 3

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

shared result series: 39
distinct benchmarks: 11
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 Grok 4.5 and Mistral Large 3
Attribute	Grok 4.5	Mistral Large 3
Provider	xAI	Mistral AI
Released	Jul 16, 2026	Dec 2, 2025
Availability	Active	Active
Model type	Proprietary	Open Weights
Parameters	Not published	675B, 41B active
Architecture	Not published	Mixture of Experts
Context window	500,000 tokens	262,144 tokens
Knowledge cutoff	February 1, 2026	Not published
Technical sources	Model	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 Grok 4.5 and Mistral Large 3
Price type	Grok 4.5	Mistral Large 3
API input	$2 ≤200K / $4 >200K	$0.5
API output	$6 ≤200K / $12 >200K	$1.5
Cache read	$0.3 ≤200K / $0.6 >200K	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

Grok 4.5Mistral Large 3

API inputUSD per 1M tokens, base tier

Grok 4.5$2

Mistral Large 3$0.5

API outputUSD per 1M tokens, base tier

Grok 4.5$6

Mistral Large 3$1.5

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Grok 4.5 and Mistral Large 3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Grok 4.5	xAI	Direct from developerUp to 200,000 context tokens	Lowest listed price: $2	Lowest listed price: $6	Source09/22/2026
	xAI	Direct from developerAbove 200,000 context tokens	$4	$12	Source09/22/2026
	xAI	Via OpenRouterxai	Lowest listed price: $2	Lowest listed price: $6	Source10/02/2026
	xAI	Via OpenRouterxai/priority	$4	$12	Source10/02/2026
	xAI	Via OpenRouterxai/zdr	Lowest listed price: $2	Lowest listed price: $6	Source10/02/2026
	xAI	Via OpenRouterxai/zdr/priority	$4	$12	Source10/02/2026
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

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.

Grok 4.5

Mistral Large 3

Coding: 100 / 69.4 (3 benchmark families)

Reasoning: 100 / 84.9 (2 benchmark families)

Mathematics: 100 / 95 (1 benchmark family)

Knowledge: 100 / 92.6 (2 benchmark families)

Finance: 99.5 / 92.8 (4 benchmark families)

Legal: 100 / 94.2 (2 benchmark families)

Multimodal: 93.4 / 100 (1 benchmark family)

Health: 100 / 97.5 (1 benchmark family)

39 matched rows from 11 benchmark families were considered. The radar shows 8 of 10 comparable categories.

Grok 4.5Mistral Large 3

CorpFin v2Overall. Higher is better. No documented setup difference

Grok 4.567.405 %

Mistral Large 361.033 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Grok 4.592.929 %

Mistral Large 368.434 %

LegalBenchOverall. Higher is better. No documented setup difference

Grok 4.585.965 %

Mistral Large 379.138 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Grok 4.587.351 %

Mistral Large 355.337 %

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

Grok 4.51,465.414

Mistral Large 31,413.254

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

Grok 4.589.216 %

Mistral Large 379.823 %

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

Grok 4.561.792 %

Mistral Large 366.185 %

MortgageTaxOverall. Higher is better. No documented setup difference

Grok 4.561.804 %

Mistral Large 352.106 %

SAGEOverall. Higher is better. No documented setup difference

Grok 4.534.967 %

Mistral Large 324.595 %

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

Grok 4.586.6 %

Mistral Large 341.4 %

TaxEval v2Overall. Higher is better. No documented setup difference

Grok 4.571.668 %

Mistral Large 373.058 %

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

Grok 4.51,465.004

Mistral Large 31,409.446

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.

Grok 4.5

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: x-ai/grok-4.5
Reasoning setting: high
Pinned endpoint: xAI | x-ai/grok-4.5-20260708
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 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.

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 Grok 4.5 and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Benchmark scores for Grok 4.5 and Mistral Large 3
Benchmark and task	Grok 4.5	Mistral Large 3	Source
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner67.405 %	61.033 %	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	Winner92.929 %	68.434 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner85.965 %	79.138 %	Vals AI Source details Data as of: 09/27/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner87.351 %	55.337 %	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 37,535 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 77,456 anonymous pairwise votes.	Winner1,465.414 95% confidence interval: ±4.412The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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	Winner89.216 %	79.823 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	61.792 %	Winner66.185 %	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	Winner61.804 %	52.106 %	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	Winner34.967 %	24.595 %	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	Winner86.6 %	41.4 %	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	71.668 %	Winner73.058 %	Vals AI 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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 7,290 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 14,597 anonymous pairwise votes.	Winner1,465.004 95% confidence interval: ±7.724The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlChinese Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 2,896 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,845 anonymous pairwise votes.	Winner1,505.755 95% confidence interval: ±11.632The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlCoding Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 10,550 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,574 anonymous pairwise votes.	Winner1,513.191 95% confidence interval: ±6.775The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 7,601 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,448 anonymous pairwise votes.	Winner1,451.609 95% confidence interval: ±7.898The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 15,071 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 32,060 anonymous pairwise votes.	Winner1,474.622 95% confidence interval: ±5.858The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 9,639 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,716 anonymous pairwise votes.	Winner1,445.916 95% confidence interval: ±7.14The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 28,109 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 56,501 anonymous pairwise votes.	Winner1,471.96 95% confidence interval: ±5.785The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlExpert prompts Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 4,428 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 7,295 anonymous pairwise votes.	Winner1,488.107 95% confidence interval: ±9.506The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlFrench Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 1,205 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,181 anonymous pairwise votes.	Winner1,481.143 95% confidence interval: ±18.817The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlGerman Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 624 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,257 anonymous pairwise votes.	Winner1,460.912 95% confidence interval: ±24.162The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 25,239 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 47,316 anonymous pairwise votes.	Winner1,488.519 95% confidence interval: ±5.113The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 10,073 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,638 anonymous pairwise votes.	Winner1,494.083 95% confidence interval: ±6.818The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 13,752 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 24,861 anonymous pairwise votes.	Winner1,462.307 95% confidence interval: ±6.192The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlJapanese Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 494 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 830 anonymous pairwise votes.	Winner1,438.475 95% confidence interval: ±28.331The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,382.659 95% confidence interval: ±22.106The 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 setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 677 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,318 anonymous pairwise votes.	Winner1,414.178 95% confidence interval: ±23.879The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 3,192 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,879 anonymous pairwise votes.	Winner1,475.752 95% confidence interval: ±11.253The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	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 setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 6,168 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 12,690 anonymous pairwise votes.	Winner1,485.218 95% confidence interval: ±8.129The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlLonger queries Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 18,276 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 29,146 anonymous pairwise votes.	Winner1,480.938 95% confidence interval: ±5.775The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMath Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 1,625 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,411 anonymous pairwise votes.	Winner1,470.716 95% confidence interval: ±14.748The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMathematical professions Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 2,010 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,047 anonymous pairwise votes.	Winner1,491.811 95% confidence interval: ±13.662The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 2,770 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,443 anonymous pairwise votes.	Winner1,466.044 95% confidence interval: ±12.08The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,430.076 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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlMulti-turn Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 6,305 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,164 anonymous pairwise votes.	Winner1,473.221 95% confidence interval: ±8.236The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlNon-English Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 22,456 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 45,384 anonymous pairwise votes.	Winner1,454.241 95% confidence interval: ±5.21The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlPolish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 585 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,754 anonymous pairwise votes.	Winner1,452.934 95% confidence interval: ±24.216The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlRussian Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 4,359 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,292 anonymous pairwise votes.	Winner1,464.004 95% confidence interval: ±9.479The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 15,148 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 29,068 anonymous pairwise votes.	Winner1,501.977 95% confidence interval: ±5.911The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
LMArena Text, Style ControlSpanish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 1,046 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,328 anonymous pairwise votes.	Winner1,461.294 95% confidence interval: ±19.175The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,405.285 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.	LMArena Source details Data as of: 09/25/2026
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 betterGrok 4.5: Snapshot: grok-4.5, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGrok 4.5: Style-controlled Arena rating from 10,131 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,002 anonymous pairwise votes.	Winner1,459.051 95% confidence interval: ±6.932The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	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.	LMArena Source details Data as of: 09/25/2026
Key to the marks:better valuebetter, but not conclusivetie