Head-to-head comparison

GLM-5.1 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: 37
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 GLM-5.1 and Mistral Large 3
Attribute	GLM-5.1	Mistral Large 3
Provider	Z.ai	Mistral AI
Released	Apr 7, 2026	Dec 2, 2025
Availability	Open Source	Active
Model type	Open Weights	Open Weights
Parameters	744B, 40B active	675B, 41B active
Architecture	Mixture of Experts	Mixture of Experts
Context window	200,000 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 GLM-5.1 and Mistral Large 3
Price type	GLM-5.1	Mistral Large 3
API input	$1.4	$0.5
API output	$4.4	$1.5
Cache read	$0.26	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

GLM-5.1Mistral Large 3

API inputUSD per 1M tokens, base tier

GLM-5.1$1.4

Mistral Large 3$0.5

API outputUSD per 1M tokens, base tier

GLM-5.1$4.4

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 GLM-5.1 and Mistral Large 3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GLM-5.1	Z.ai	Direct from developerStandard API	$1.4	$4.4	Source09/22/2026
	Alibaba	Via OpenRouteralibaba/fp8	$1.33	$4.18	Source10/03/2026
	Friendli	Via OpenRouterfriendli	$1.4	$4.4	Source10/03/2026
	Nebius	Via OpenRouternebius/fp8	$1.4	$4.4	Source10/03/2026
	Novita	Via OpenRouternovita/fp8	$1.38	$4.4	Source10/03/2026
	SiliconFlow	Via OpenRoutersiliconflow/fp8	$1.19	$3.74	Source10/03/2026
	StreamLake	Via OpenRouterstreamlake/fp8	Lowest listed price: $0.966	Lowest listed price: $3.036	Source10/03/2026
	Venice	Via OpenRoutervenice/fp8	$1.4014	$4.4044	Source10/03/2026
	Z.AI	Via OpenRouterz-ai/fp8	$1.4	$4.4	Source10/03/2026
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	Source10/03/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source10/03/2026

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.

GLM-5.1

Mistral Large 3

Coding: 100 / 73.1 (3 benchmark families)

Reasoning: 100 / 88.4 (2 benchmark families)

Mathematics: 100 / 95.5 (1 benchmark family)

Knowledge: 100 / 93.8 (2 benchmark families)

Finance: 99.1 / 97 (3 benchmark families)

Legal: 100 / 95.2 (2 benchmark families)

Agentic tasks: 100 / 16.7 (1 benchmark family)

Health: 100 / 96.2 (1 benchmark family)

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

GLM-5.1Mistral Large 3

CorpFin v2Overall. Higher is better. No documented setup difference

GLM-5.164.452 %

Mistral Large 361.033 %

GPQA DiamondOverall. Higher is better. No documented setup difference

GLM-5.184.518 %

Mistral Large 368.434 %

LegalBenchOverall. Higher is better. No documented setup difference

GLM-5.184.394 %

Mistral Large 379.138 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

GLM-5.181.38 %

Mistral Large 355.337 %

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

GLM-5.11,465.068

Mistral Large 31,413.254

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

GLM-5.186.9 %

Mistral Large 379.823 %

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

GLM-5.176.4 %

Mistral Large 341.4 %

TaxEval v2Overall. Higher is better. No documented setup difference

GLM-5.171.194 %

Mistral Large 373.058 %

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

GLM-5.153.933 %

Mistral Large 38.989 %

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

GLM-5.11,465.322

Mistral Large 31,409.446

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

GLM-5.11,515.399

Mistral Large 31,434.058

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

GLM-5.11,513.13

Mistral Large 31,469.182

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 latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

GLM-5.1

Output withheld for safety

Reasoning (requested): high

Current attempt

Run date: 2 Oct 2026
API provider: openrouter
Requested API model: z-ai/glm-5.1
API model reported in response: z-ai/glm-5.1
Reasoning setting: high
Pinned endpoint: Z.AI | z-ai/glm-5.1-20260406
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 178.8 s

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

Earlier attempts (2)

1 Oct 2026API request failedReasoning setting: high
7 Sept 2026API request failedReasoning setting: high

Mistral Large 3

Reasoning (model default): no reasoning mode Source

Current attempt

Run date: 1 Oct 2026
API provider: openrouter
Requested API model: mistralai/mistral-large-2512
API model reported in response: 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: Passed, not a quality rating
Response time: 14.2 s

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (1)

7 Sept 2026API request failedReasoning setting: not specified

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 GLM-5.1 and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Benchmark scores for GLM-5.1 and Mistral Large 3
Benchmark and task	GLM-5.1	Mistral Large 3	Source
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner64.452 %	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	Winner84.518 %	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	Winner84.394 %	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	Winner81.38 %	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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 56,463 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 77,456 anonymous pairwise votes.	Winner1,465.068 95% confidence interval: ±3.715The 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	Winner86.9 %	79.823 %	Vals AI Source details Data as of: 09/01/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner76.4 %	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	71.194 %	Winner73.058 %	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	Winner53.933 %	8.989 %	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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 11,108 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 14,597 anonymous pairwise votes.	Winner1,465.322 95% confidence interval: ±6.481The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 3,907 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,845 anonymous pairwise votes.	Winner1,515.399 95% confidence interval: ±10.138The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 15,660 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,574 anonymous pairwise votes.	Winner1,513.13 95% confidence interval: ±5.733The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 10,727 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,448 anonymous pairwise votes.	Winner1,447.707 95% confidence interval: ±6.774The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 24,378 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 32,060 anonymous pairwise votes.	Winner1,481.044 95% confidence interval: ±4.821The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 13,137 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 16,716 anonymous pairwise votes.	Winner1,441.928 95% confidence interval: ±6.228The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 42,223 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 56,501 anonymous pairwise votes.	Winner1,471.413 95% confidence interval: ±4.862The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 6,038 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 7,295 anonymous pairwise votes.	Winner1,494.948 95% confidence interval: ±8.28The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 1,950 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,181 anonymous pairwise votes.	Winner1,489.103 95% confidence interval: ±15.177The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 897 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,257 anonymous pairwise votes.	Winner1,466.818 95% confidence interval: ±20.602The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 37,327 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 47,316 anonymous pairwise votes.	Winner1,488.247 95% confidence interval: ±4.323The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 16,460 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,638 anonymous pairwise votes.	Winner1,499.442 95% confidence interval: ±5.631The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 19,895 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 24,861 anonymous pairwise votes.	Winner1,460.457 95% confidence interval: ±5.219The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 727 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 830 anonymous pairwise votes.	Winner1,437.526 95% confidence interval: ±23.963The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 1,078 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,318 anonymous pairwise votes.	Winner1,418.73 95% confidence interval: ±19.425The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 4,441 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,879 anonymous pairwise votes.	Winner1,471.68 95% confidence interval: ±9.459The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 9,303 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 12,690 anonymous pairwise votes.	Winner1,487.697 95% confidence interval: ±6.836The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 25,751 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 29,146 anonymous pairwise votes.	Winner1,479.775 95% confidence interval: ±5.005The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,417.29 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 2,761 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,411 anonymous pairwise votes.	Winner1,475.239 95% confidence interval: ±11.676The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 3,068 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 4,047 anonymous pairwise votes.	Winner1,473.237 95% confidence interval: ±11.264The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 4,067 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 5,443 anonymous pairwise votes.	Winner1,486.312 95% confidence interval: ±9.939The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 9,068 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 13,164 anonymous pairwise votes.	Winner1,479.315 95% confidence interval: ±6.985The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 32,079 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 45,384 anonymous pairwise votes.	Winner1,448.598 95% confidence interval: ±4.422The 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 setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 1,047 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 1,754 anonymous pairwise votes.	No clear lead1,443.495 95% confidence interval: ±18.109The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 6,608 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 9,292 anonymous pairwise votes.	Winner1,456.883 95% confidence interval: ±7.848The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 22,489 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 29,068 anonymous pairwise votes.	Winner1,502.141 95% confidence interval: ±4.987The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 1,859 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 2,328 anonymous pairwise votes.	Winner1,464.202 95% confidence interval: ±14.659The 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 betterGLM-5.1: Snapshot: glm-5.1, Harness: Arena text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena text, style controlGLM-5.1: Style-controlled Arena rating from 14,723 anonymous pairwise votes.Mistral Large 3: Style-controlled Arena rating from 19,002 anonymous pairwise votes.	Winner1,453.152 95% confidence interval: ±5.895The 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