Head-to-head comparison

GPT-6 Astra 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: 45
distinct benchmark metrics: 4
latest retrieval: 2026-10-15

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 GPT-6 Astra and Mistral Large 3
Attribute	GPT-6 Astra	Mistral Large 3
Provider	OpenAI	Mistral AI
Released	Sep 3, 2026	Dec 2, 2025
Availability	Limited access	Active
Model type	Proprietary	Open Weights
Parameters	Not published	675B, 41B active
Architecture	Not published	Mixture of Experts
Context window	1,050,000 tokens	262,144 tokens
Knowledge cutoff	April 30, 2026	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 GPT-6 Astra and Mistral Large 3
Price type	GPT-6 Astra	Mistral Large 3
API input	$10 ≤272K / $20 >272K	$0.5
API output	$50 ≤272K / $75 >272K	$1.5
Cache read	$1 ≤272K / $2 >272K	Not listed
Cache write (5 min.)	$12.5 ≤272K / $25 >272K	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

GPT-6 AstraMistral Large 3

API inputUSD per 1M tokens, base tier

GPT-6 Astra$10

Mistral Large 3$0.5

API outputUSD per 1M tokens, base tier

GPT-6 Astra$50

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 GPT-6 Astra and Mistral Large 3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
GPT-6 Astra	OpenAI	Direct from developerUp to 272,000 context tokens	$10	$50	Source09/22/2026
	OpenAI	Direct from developerAbove 272,000 context tokens	$20	$75	Source09/22/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-west-2	$11	$55	Source10/19/2026
	Azure	Via OpenRouterazure	$10	$50	Source10/19/2026
	Azure	Via OpenRouterazure/us	$11	$55	Source10/19/2026
	OpenAI	Via OpenRouteropenai	$10	$50	Source10/19/2026
	OpenAI	Via OpenRouteropenai/fast	$20	$100	Source10/19/2026
	OpenAI	Via OpenRouteropenai/flex	Lowest listed price: $5	Lowest listed price: $25	Source10/19/2026
	OpenAI	Via OpenRouteropenai/ultrafast	$60	$300	Source10/19/2026
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	Source10/19/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source10/19/2026

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.

Not enough directly matched categories for a reliable radar

Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

GPT-6 AstraMistral Large 3

LMArena Code Arena WebDevOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra1,780.244

Mistral Large 31,230.205

LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra1,476.716

Mistral Large 31,414.136

LMArena Vision, Style ControlOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra1,285.988

Mistral Large 31,199.757

SAGEOverall. Higher is better. Test setup not documented as identical

GPT-6 Astra46.367 %

Mistral Large 324.595 %

LMArena Code Arena WebDevImage to webdev. Higher is better. Test setup not documented as identical

GPT-6 Astra1,731.395

Mistral Large 31,361.78

LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical

GPT-6 Astra1,472.34

Mistral Large 31,409.853

LMArena Vision, Style ControlChinese. Higher is better. Test setup not documented as identical

GPT-6 Astra1,357.126

Mistral Large 31,211.728

SAGEAutomata. Higher is better. Test setup not documented as identical

GPT-6 Astra37.302 %

Mistral Large 311.905 %

LMArena Code Arena WebDevWebdev. Higher is better. Test setup not documented as identical

GPT-6 Astra1,780.244

Mistral Large 31,230.205

LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical

GPT-6 Astra1,514.537

Mistral Large 31,432.609

LMArena Vision, Style ControlCreative writing vision. Higher is better. Test setup not documented as identical

GPT-6 Astra1,289.081

Mistral Large 31,196.146

SAGECalculus. Higher is better. Test setup not documented as identical

GPT-6 Astra79.938 %

Mistral Large 30 %

Key to the marks:better valuebetter, but not conclusivetie

Our model tests

Our tests

SVG short test

One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.

Shared test round: 4ae5d8eeb9a9

GPT-6 Astra

Unavailable in this round

Mistral Large 3

API request failed. The model was not evaluated.

Earlier tests

Pelican on a bicycle

A community classic for free-form SVG drawing.

GPT-6 Astra

Reasoning (requested): high

Current attempt

Run date: Sep 7, 2026
API provider: openrouter
Requested API model: openai/gpt-6-astra
API model reported in response: openai/gpt-6-astra
Reasoning setting: high
Pinned endpoint: OpenAI | openai/gpt-6-astra-20260903
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: 141.7 s

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

Mistral Large 3

Reasoning (model default): no reasoning mode Source

Current attempt

Run date: Oct 1, 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)

Sep 7, 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 GPT-6 Astra and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Benchmark scores for GPT-6 Astra and Mistral Large 3
Benchmark and task	GPT-6 Astra	Mistral Large 3	Source
LMArena Code Arena WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,780.244 95% confidence interval: ±10.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,230.205 95% confidence interval: ±25.485The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 11,674 published pairwise votes.Mistral Large 3: Arena rating from 83,498 published pairwise votes.	Higher measured value1,476.716 95% confidence interval: ±6.385The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,414.136 95% confidence interval: ±2.865The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 3,590 published pairwise votes.Mistral Large 3: Arena rating from 8,643 published pairwise votes.	Higher measured value1,285.988 95% confidence interval: ±10.782The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,199.757 95% confidence interval: ±7.981The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
SAGEOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value46.367 %	24.595 %	Vals AI Source details Data as of: 10/08/2026
LMArena Code Arena WebDevImage to webdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 2,739 published pairwise votes.Mistral Large 3: Arena rating from 1,413 published pairwise votes.	Higher measured value1,731.395 95% confidence interval: ±13.296The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,361.78 95% confidence interval: ±17.387The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
LMArena Text, Style ControlBusiness, management and finance Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,061 published pairwise votes.Mistral Large 3: Arena rating from 15,540 published pairwise votes.	Higher measured value1,472.34 95% confidence interval: ±13.336The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,409.853 95% confidence interval: ±5.362The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 230 published pairwise votes.Mistral Large 3: Arena rating from 540 published pairwise votes.	Higher measured value1,357.126 95% confidence interval: ±39.572The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,211.728 95% confidence interval: ±27.072The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value37.302 %	11.905 %	Vals AI Source details Data as of: 10/08/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 5,746 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,780.244 95% confidence interval: ±10.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,230.205 95% confidence interval: ±25.485The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 877 published pairwise votes.Mistral Large 3: Arena rating from 6,341 published pairwise votes.	Higher measured value1,514.537 95% confidence interval: ±19.541The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.609 95% confidence interval: ±7.919The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlCreative writing vision Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 367 published pairwise votes.Mistral Large 3: Arena rating from 807 published pairwise votes.	Higher measured value1,289.081 95% confidence interval: ±32.749The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,196.146 95% confidence interval: ±22.467The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
SAGECalculus Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value79.938 %	0 %	Vals AI Source details Data as of: 10/08/2026
LMArena Code Arena WebDevWebdev-html Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevGPT-6 Astra: Arena rating from 1,129 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,780.13 95% confidence interval: ±22.887The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,238.427 95% confidence interval: ±26.132The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlCoding Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,659 published pairwise votes.Mistral Large 3: Arena rating from 21,009 published pairwise votes.	Higher measured value1,543.161 95% confidence interval: ±11.756The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,470.833 95% confidence interval: ±4.783The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlDiagram Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 861 published pairwise votes.Mistral Large 3: Arena rating from 2,169 published pairwise votes.	Higher measured value1,310.509 95% confidence interval: ±20.739The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,235.106 95% confidence interval: ±13.517The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value62.117 %	44.419 %	Vals AI Source details Data as of: 10/08/2026
LMArena Text, Style ControlCreative writing Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,620 published pairwise votes.Mistral Large 3: Arena rating from 14,972 published pairwise votes.	Higher measured value1,449.578 95% confidence interval: ±12.436The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,373.958 95% confidence interval: ±5.611The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlEnglish Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 1,205 published pairwise votes.Mistral Large 3: Arena rating from 2,983 published pairwise votes.	Higher measured value1,288.398 95% confidence interval: ±17.904The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,210.278 95% confidence interval: ±12.173The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
SAGEPartial Differential Equations Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterGPT-6 Astra: Reasoning: max, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value39.683 %	17.46 %	Vals AI Source details Data as of: 10/08/2026
LMArena Text, Style ControlEnglish Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 4,703 published pairwise votes.Mistral Large 3: Arena rating from 34,656 published pairwise votes.	Higher measured value1,485.113 95% confidence interval: ±9.08The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,426.99 95% confidence interval: ±3.961The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlHomework Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 480 published pairwise votes.Mistral Large 3: Arena rating from 891 published pairwise votes.	Higher measured value1,346.15 95% confidence interval: ±26.584The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,211.931 95% confidence interval: ±20.61The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
LMArena Text, Style ControlEntertainment, sports and media Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,996 published pairwise votes.Mistral Large 3: Arena rating from 18,448 published pairwise votes.	Higher measured value1,458.633 95% confidence interval: ±11.598The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,372.089 95% confidence interval: ±5.132The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Vision, Style ControlOcr Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlGPT-6 Astra: Arena rating from 2,449 published pairwise votes.Mistral Large 3: Arena rating from 5,778 published pairwise votes.	Higher measured value1,301.633 95% confidence interval: ±12.448The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,215.499 95% confidence interval: ±8.709The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/09/2026
LMArena Text, Style ControlExcluding ties Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 8,636 published pairwise votes.Mistral Large 3: Arena rating from 61,071 published pairwise votes.	Higher measured value1,488.868 95% confidence interval: ±8.374The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,401.523 95% confidence interval: ±3.976The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlExpert prompts Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 1,132 published pairwise votes.Mistral Large 3: Arena rating from 7,976 published pairwise votes.	Higher measured value1,509.902 95% confidence interval: ±17.672The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,427.286 95% confidence interval: ±7.215The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlFrench Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 333 published pairwise votes.Mistral Large 3: Arena rating from 2,379 published pairwise votes.	Higher measured value1,489.442 95% confidence interval: ±32.984The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.543 95% confidence interval: ±13.786The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlGerman Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 176 published pairwise votes.Mistral Large 3: Arena rating from 1,359 published pairwise votes.	Higher measured value1,480.596 95% confidence interval: ±44.81The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,407.953 95% confidence interval: ±17.201The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlHard prompts Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 7,117 published pairwise votes.Mistral Large 3: Arena rating from 50,980 published pairwise votes.	Higher measured value1,502.017 95% confidence interval: ±7.647The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.155 95% confidence interval: ±3.56The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlHard prompts, English Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 2,847 published pairwise votes.Mistral Large 3: Arena rating from 21,186 published pairwise votes.	Higher measured value1,505.128 95% confidence interval: ±11.467The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,439.589 95% confidence interval: ±4.785The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlInstruction following Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 3,666 published pairwise votes.Mistral Large 3: Arena rating from 26,939 published pairwise votes.	Higher measured value1,471.988 95% confidence interval: ±10.084The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,401.72 95% confidence interval: ±4.374The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlJapanese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 220 published pairwise votes.Mistral Large 3: Arena rating from 929 published pairwise votes.	Higher measured value1,429.026 95% confidence interval: ±42.875The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,379.052 95% confidence interval: ±21.069The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlKorean Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 210 published pairwise votes.Mistral Large 3: Arena rating from 1,428 published pairwise votes.	Higher measured value1,450.643 95% confidence interval: ±41.535The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,358.651 95% confidence interval: ±17.119The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlLegal and government Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 1,000 published pairwise votes.Mistral Large 3: Arena rating from 6,347 published pairwise votes.	Higher measured value1,486.122 95% confidence interval: ±18.889The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,420.684 95% confidence interval: ±7.935The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlLife, physical and social science Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 1,987 published pairwise votes.Mistral Large 3: Arena rating from 13,640 published pairwise votes.	Higher measured value1,489.3 95% confidence interval: ±13.614The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,428.444 95% confidence interval: ±5.571The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlLonger queries Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 4,917 published pairwise votes.Mistral Large 3: Arena rating from 31,737 published pairwise votes.	Higher measured value1,488.357 95% confidence interval: ±9.148The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,417.413 95% confidence interval: ±4.313The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlMath Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 587 published pairwise votes.Mistral Large 3: Arena rating from 4,742 published pairwise votes.	Higher measured value1,481.638 95% confidence interval: ±23.784The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,400.815 95% confidence interval: ±8.893The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlMathematical professions Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 664 published pairwise votes.Mistral Large 3: Arena rating from 4,407 published pairwise votes.	Higher measured value1,495.728 95% confidence interval: ±22.879The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,413.768 95% confidence interval: ±9.421The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlMedicine and healthcare Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 841 published pairwise votes.Mistral Large 3: Arena rating from 5,848 published pairwise votes.	Higher measured value1,469.187 95% confidence interval: ±20.767The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,431.33 95% confidence interval: ±8.313The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlMulti-turn Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 1,593 published pairwise votes.Mistral Large 3: Arena rating from 14,021 published pairwise votes.	Higher measured value1,485.974 95% confidence interval: ±15.121The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,420.254 95% confidence interval: ±5.589The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026
LMArena Text, Style ControlNon-English Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-6 Astra: Snapshot: gpt-6-astra-max, Reasoning: max, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlGPT-6 Astra: Arena rating from 6,968 published pairwise votes.Mistral Large 3: Arena rating from 48,836 published pairwise votes.	Higher measured value1,463.829 95% confidence interval: ±7.687The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,398.12 95% confidence interval: ±3.514The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	LMArena Source details Data as of: 10/13/2026

GPT-6 Astra vs. Mistral Large 3

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

GPT-6 Astra

Mistral Large 3

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons