Head-to-head comparison

Qwen 3.8 Max 0902 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: 53
distinct benchmarks: 11
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 Qwen 3.8 Max 0902 and Mistral Large 3
Attribute	Qwen 3.8 Max 0902	Mistral Large 3
Provider	Alibaba	Mistral AI
Released	Sep 2, 2026	Dec 2, 2025
Availability	API-only	Active
Model type	Proprietary	Open Weights
Parameters	2.4T	675B, 41B active
Architecture	Mixture of Experts	Mixture of Experts
Context window	1,000,000 tokens	262,144 tokens
Knowledge cutoff	Not published	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 Qwen 3.8 Max 0902 and Mistral Large 3
Price type	Qwen 3.8 Max 0902	Mistral Large 3
API input	$1.65	$0.5
API output	$4.951	$1.5
Cache read	$0.137	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

Qwen 3.8 Max 0902Mistral Large 3

API inputUSD per 1M tokens, base tier

Qwen 3.8 Max 0902$1.65

Mistral Large 3$0.5

API outputUSD per 1M tokens, base tier

Qwen 3.8 Max 0902$4.951

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 Qwen 3.8 Max 0902 and Mistral Large 3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Qwen 3.8 Max 0902	Alibaba	Direct from developerStandard API	Lowest listed price: $1.65	Lowest listed price: $4.951	Source09/22/2026
	Alibaba	Via OpenRouteralibaba	$2	$6	Source10/18/2026
	Alibaba	Via OpenRouteralibaba/us-east-1	$2	$6	Source10/18/2026
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	Source10/18/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source10/18/2026

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

Qwen 3.8 Max 0902Mistral Large 3

CorpFin v2Overall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090265.851 %

Mistral Large 361.033 %

GPQA DiamondOverall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090293.686 %

Mistral Large 368.434 %

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

Qwen 3.8 Max 090283.609 %

Mistral Large 379.138 %

LiveCodeBench v6Overall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090287.852 %

Mistral Large 355.337 %

LMArena Code Arena WebDevOverall. Higher is better. No documented setup difference

Qwen 3.8 Max 09021,673.151

Mistral Large 31,230.205

MMLU-ProOverall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090288.602 %

Mistral Large 379.823 %

MMMU-ProOverall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090288.035 %

Mistral Large 366.185 %

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

Qwen 3.8 Max 090263.99 %

Mistral Large 352.106 %

SAGEOverall. Higher is better. No documented setup difference

Qwen 3.8 Max 090251.254 %

Mistral Large 324.595 %

SWE-bench VerifiedOverall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090285.6 %

Mistral Large 341.4 %

TaxEval v2Overall. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090275.552 %

Mistral Large 373.058 %

CorpFin v2Exact Pages. Higher is better. Test setup not documented as identical

Qwen 3.8 Max 090264.569 %

Mistral Large 359.79 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Qwen 3.8 Max 0902 and Mistral Large 3
Benchmark and task	Qwen 3.8 Max 0902	Mistral Large 3	Source
CorpFin v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value65.851 %	61.033 %	Vals AI Source details Data as of: 08/12/2026
GPQA DiamondOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value93.686 %	68.434 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value83.609 %	79.138 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Overall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value87.852 %	55.337 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevOverall Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterQwen 3.8 Max 0902: Snapshot: qwen3.8-max-0902, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevQwen 3.8 Max 0902: Arena rating from 13,081 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,673.151 95% confidence interval: ±7.241The 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
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.602 %	79.823 %	Vals AI Source details Data as of: 09/01/2026
MMMU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.035 %	66.185 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value63.99 %	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 betterSettings: Temperature: 1, Output limit: 30,000 tokens	Winner51.254 %	24.595 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench VerifiedOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value85.6 %	41.4 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value75.552 %	73.058 %	Vals AI Source details Data as of: 09/01/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value64.569 %	59.79 %	Vals AI Source details Data as of: 08/12/2026
GPQA DiamondFew-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.424 %	64.141 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchConclusion Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.23 %	81.032 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Easy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value99.068 %	95.342 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevImage to webdev Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterQwen 3.8 Max 0902: Snapshot: qwen3.8-max-0902, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevQwen 3.8 Max 0902: Arena rating from 1,164 published pairwise votes.Mistral Large 3: Arena rating from 1,413 published pairwise votes.	Winner1,637.891 95% confidence interval: ±18.343The 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
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value94.142 %	88.563 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxNumerical Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value72.258 %	50 %	Vals AI Source details Data as of: 09/01/2026
SAGEAutomata Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Temperature: 1, Output limit: 30,000 tokens	Winner39.682 %	11.905 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified<15 min fix Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value93.299 %	56.186 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Correctness Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value64.105 %	61.57 %	Vals AI Source details Data as of: 09/01/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value65.618 %	63.753 %	Vals AI Source details Data as of: 08/12/2026
GPQA DiamondZero-Shot CoT Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value94.949 %	72.727 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchInterpretation Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value84.061 %	76.594 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Hard Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value75.714 %	17.143 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterQwen 3.8 Max 0902: Snapshot: qwen3.8-max-0902, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevQwen 3.8 Max 0902: Arena rating from 13,081 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,673.151 95% confidence interval: ±7.241The 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
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.902 %	84.664 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxSemantic Extraction Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value55.723 %	54.213 %	Vals AI Source details Data as of: 09/01/2026
SAGECalculus Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Temperature: 1, Output limit: 30,000 tokens	Winner71.914 %	0 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified>4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value66.667 %	33.333 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Stepwise Reasoning Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value86.999 %	84.546 %	Vals AI Source details Data as of: 09/01/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value67.366 %	59.557 %	Vals AI Source details Data as of: 08/12/2026
LegalBenchIssue Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value90.635 %	81.006 %	Vals AI Source details Data as of: 10/13/2026
LiveCodeBench v6Medium Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.773 %	53.525 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev-html Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterQwen 3.8 Max 0902: Snapshot: qwen3.8-max-0902, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevQwen 3.8 Max 0902: Arena rating from 2,257 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,651.307 95% confidence interval: ±14.717The 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
MMLU-ProChemistry Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.491 %	84.982 %	Vals AI Source details Data as of: 09/01/2026
SAGELinear Algebra Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Temperature: 1, Output limit: 30,000 tokens	Winner69.636 %	44.419 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified1-4 hours Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value64.286 %	4.762 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchRhetoric Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value79.047 %	77.926 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProComputer Science Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value90.976 %	83.171 %	Vals AI Source details Data as of: 09/01/2026
SAGEPartial Differential Equations Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Temperature: 1, Output limit: 30,000 tokens	Winner44.444 %	17.46 %	Vals AI Source details Data as of: 10/08/2026
SWE-bench Verified15 min - 1 hour Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value83.525 %	36.398 %	Vals AI Source details Data as of: 09/01/2026
LegalBenchRule Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	76.071 %	Higher measured value79.13 %	Vals AI Source details Data as of: 10/13/2026
MMLU-ProEconomics Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value89.929 %	85.782 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProEngineering Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value86.687 %	74.923 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProHealth Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value83.985 %	77.262 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProHistory Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value81.102 %	70.866 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProLaw Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value77.293 %	56.403 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProMath Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value95.485 %	88.379 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProOthers Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value85.281 %	79.221 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProPhilosophy Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.377 %	76.353 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProPhysics Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value93.303 %	86.374 %	Vals AI Source details Data as of: 09/01/2026
MMLU-ProPsychology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterQwen 3.8 Max 0902: Temperature: 0.7, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.471 %	80.576 %	Vals AI Source details Data as of: 09/01/2026
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

Qwen 3.8 Max 0902

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.

Qwen 3.8 Max 0902

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt

Run date: Oct 5, 2026
API provider: openrouter
Requested API model: qwen/qwen3.8-max-0902
API model reported in response: qwen/qwen3.8-max-0902
Reasoning setting: high
Pinned endpoint: Alibaba | qwen/qwen3.8-max-20260902
Temperature: Provider default
Token limit including reasoning: 8,192 tokens
Test protocol: community-visual-tests-v1
Technical checks: Failed
Response time: 189.9 s

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

Earlier attempts (3)

Oct 2, 2026API request failedReasoning setting: high
Oct 1, 2026API request failedReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

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 Qwen 3.8 Max 0902 and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Qwen 3.8 Max 0902 vs. Mistral Large 3

Change model selection

General specifications

API pricing compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Qwen 3.8 Max 0902

Mistral Large 3

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons