Head-to-head comparison

Claude Opus 4.8 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: 132
distinct benchmark metrics: 14
latest retrieval: 2026-10-16

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 Claude Opus 4.8 and Mistral Large 3
Attribute	Claude Opus 4.8	Mistral Large 3
Provider	Anthropic	Mistral AI
Released	May 2026	Dec 2, 2025
Availability	Legacy	Active
Model type	Proprietary	Open Weights
Parameters	Not published	675B, 41B active
Architecture	Not published	Mixture of Experts
Context window	1,000,000 tokens	262,144 tokens
Knowledge cutoff	January 2026	Not published
Technical sources	Model, Knowledge cutoff	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 Claude Opus 4.8 and Mistral Large 3
Price type	Claude Opus 4.8	Mistral Large 3
API input	$5	$0.5
API output	$25	$1.5
Cache read	$0.5	Not listed
Cache write (5 min.)	$6.25	Not listed
Cache write (1 hr.)	$10	Not listed
Price verified	09/22/2026 Source	09/22/2026 Source

Claude Opus 4.8Mistral Large 3

API inputUSD per 1M tokens, base tier

Claude Opus 4.8$5

Mistral Large 3$0.5

API outputUSD per 1M tokens, base tier

Claude Opus 4.8$25

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.

No provider tariff for Claude Opus 4.8 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for Claude Opus 4.8 and Mistral Large 3
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Claude Opus 4.8	Anthropic	Direct from developerStandard API	Lowest listed price: $5	Lowest listed price: $25	Source09/22/2026
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	Source10/26/2026
	Mistral	Via OpenRoutermistral/zdr	Lowest listed price: $0.5	Lowest listed price: $1.5	Source10/26/2026

Benchmark index

Benchmark index compared

The index combines independent benchmarks on a scale from 0 to 100. A lead only counts when a model comes first in at least 95% of 200 recalculations with randomly redrawn test families. Otherwise both count as level.

Open the AI leaderboard

Claude Opus 4.8

Overall index

57.0

Mistral Large 3

Overall index

below 1

Claude Opus 4.8 leads in 10 of 10 shared areas.

Area	Claude Opus 4.8	Mistral Large 3
Coding	55.3	below 1
Reasoning	46.2	below 1
Knowledge	65.6	below 1
Agents	56.7	below 1
General	45.3	below 1
Finance	65.0	below 1
Legal	57.4	below 1
Health	67.8	below 1
Multimodal	55.0	below 1
Education	71.1	below 1

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.

Claude Opus 4.8

Mistral Large 3

Coding: 100 / 88.3 (2 benchmark families)

Reasoning: 100 / 95 (1 benchmark family)

Mathematics: 100 / 94.9 (1 benchmark family)

Knowledge: 100 / 94.5 (1 benchmark family)

Finance: 100 / 94.9 (1 benchmark family)

Legal: 100 / 94.9 (1 benchmark family)

Multimodal: 100 / 93.3 (1 benchmark family)

Health: 100 / 95.6 (1 benchmark family)

40 matched rows from 3 benchmark families were considered. The radar shows 8 of 9 comparable categories.

Claude Opus 4.8Mistral Large 3

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

Claude Opus 4.866.706 %

Mistral Large 361.033 %

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

Claude Opus 4.892.424 %

Mistral Large 368.434 %

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

Claude Opus 4.883.568 %

Mistral Large 379.138 %

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

Claude Opus 4.887.819 %

Mistral Large 355.337 %

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

Claude Opus 4.81,536.177

Mistral Large 31,230.205

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

Claude Opus 4.81,474.319

Mistral Large 31,414.247

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

Claude Opus 4.81,278.955

Mistral Large 31,199.757

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

Claude Opus 4.889.585 %

Mistral Large 379.823 %

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

Claude Opus 4.886.59 %

Mistral Large 366.185 %

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

Claude Opus 4.869.912 %

Mistral Large 352.106 %

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

Claude Opus 4.854.788 %

Mistral Large 324.595 %

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

Claude Opus 4.888.6 %

Mistral Large 341.4 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Claude Opus 4.8 and Mistral Large 3
Benchmark and task	Claude Opus 4.8	Mistral Large 3	Source
CorpFin v2Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value66.706 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.424 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value83.568 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value87.819 %	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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,536.177 95% confidence interval: ±5.702The 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 No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 65,172 published pairwise votes.Mistral Large 3: Arena rating from 84,205 published pairwise votes.	Winner1,474.319 95% confidence interval: ±3.846The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,414.247 95% confidence interval: ±2.861The 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: 10/15/2026
LMArena Vision, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 18,852 published pairwise votes.Mistral Large 3: Arena rating from 8,643 published pairwise votes.	Winner1,278.955 95% confidence interval: ±6.534The 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
MMLU-ProOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value89.585 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value86.59 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value69.912 %	52.106 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value54.788 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.6 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value75.634 %	73.058 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Overall Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value70.037 %	8.989 %	Vals AI Source details Data as of: 06/04/2026
CorpFin v2Exact Pages Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value64.336 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value91.919 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.937 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, 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 WebDevOverall Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 18,540 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,555.99 95% confidence interval: ±5.768The 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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 64,100 published pairwise votes.Mistral Large 3: Arena rating from 84,205 published pairwise votes.	Higher measured value1,481.495 95% confidence interval: ±3.868The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,414.247 95% confidence interval: ±2.861The 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: 10/15/2026
LMArena Vision, Style ControlOverall Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 18,341 published pairwise votes.Mistral Large 3: Arena rating from 8,643 published pairwise votes.	Higher measured value1,285.632 95% confidence interval: ±6.5The 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
MMLU-ProBiology Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value94.7 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value79.73 %	50 %	Vals AI Source details Data as of: 09/01/2026
SAGEAutomata Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value41.666 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.784 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value64.513 %	61.57 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Easy Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value91.667 %	50 %	Vals AI Source details Data as of: 06/04/2026
CorpFin v2Max Fitting Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value69.814 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.929 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value82.703 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value74.571 %	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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 17,454 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,536.177 95% confidence interval: ±5.702The 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 ControlBusiness, management and finance Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 12,774 published pairwise votes.Mistral Large 3: Arena rating from 15,657 published pairwise votes.	Winner1,486.109 95% confidence interval: ±6.333The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,410.175 95% confidence interval: ±5.349The 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: 10/15/2026
LMArena Vision, Style ControlChinese Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 1,131 published pairwise votes.Mistral Large 3: Arena rating from 540 published pairwise votes.	Winner1,334.517 95% confidence interval: ±19.635The 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
MMLU-ProBusiness Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.649 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value60.095 %	54.213 %	Vals AI Source details Data as of: 09/01/2026
SAGELinear Algebra Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value78.253 %	44.419 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, 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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value86.754 %	84.546 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Hard Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value54.444 %	0 %	Vals AI Source details Data as of: 06/04/2026
CorpFin v2Shared Max Context Test details Test setup not documented as identicalNo direct winnerVersion: 2Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value65.967 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value87.834 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value89.817 %	53.525 %	Vals AI Source details Data as of: 09/01/2026
LMArena Code Arena WebDevWebdev Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 18,540 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,555.99 95% confidence interval: ±5.768The 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 ControlBusiness, management and finance Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 12,750 published pairwise votes.Mistral Large 3: Arena rating from 15,657 published pairwise votes.	Higher measured value1,488.758 95% confidence interval: ±6.371The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,410.175 95% confidence interval: ±5.349The 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: 10/15/2026
LMArena Vision, Style ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 1,024 published pairwise votes.Mistral Large 3: Arena rating from 540 published pairwise votes.	Higher measured value1,332.781 95% confidence interval: ±20.343The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,211.728 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
MMLU-ProChemistry Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.845 %	84.982 %	Vals AI Source details Data as of: 09/01/2026
SAGEPartial Differential Equations Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 30,000 tokens Mistral Large 3: Temperature: 1, Output limit: 30,000 tokens	Higher measured value44.444 %	17.46 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value73.81 %	4.762 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.0Medium Test details Test setup not documented as identicalNo direct winnerVersion: 2.0Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value76.97 %	10.909 %	Vals AI Source details Data as of: 06/04/2026
LegalBenchRhetoric Tasks Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value78.389 %	77.926 %	Vals AI Source details Data as of: 10/13/2026
LMArena Code Arena WebDevWebdev-html Test details No documented difference in the test setupVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 2,434 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Winner1,524.579 95% confidence interval: ±12.803The 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 ControlChinese Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 4,397 published pairwise votes.Mistral Large 3: Arena rating from 6,405 published pairwise votes.	Winner1,524.914 95% confidence interval: ±9.61The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.412 95% confidence interval: ±7.886The 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: 10/15/2026
LMArena Vision, Style ControlCreative writing vision Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 1,394 published pairwise votes.Mistral Large 3: Arena rating from 807 published pairwise votes.	Winner1,280.145 95% confidence interval: ±16.809The 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
MMLU-ProComputer Science Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value92.683 %	83.171 %	Vals AI Source details Data as of: 09/01/2026
SWE-bench Verified15 min - 1 hour Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value88.123 %	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 betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value79.976 %	79.13 %	Vals AI Source details Data as of: 10/13/2026
LMArena Code Arena WebDevWebdev-html Test details Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Code Arena WebDev Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Code Arena WebDevClaude Opus 4.8: Arena rating from 2,269 published pairwise votes.Mistral Large 3: Arena rating from 839 published pairwise votes.	Higher measured value1,543.179 95% confidence interval: ±13.758The 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 ControlChinese Test details Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 4,372 published pairwise votes.Mistral Large 3: Arena rating from 6,405 published pairwise votes.	Higher measured value1,525.992 95% confidence interval: ±9.609The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,432.412 95% confidence interval: ±7.886The 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: 10/15/2026
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 betterClaude Opus 4.8: Snapshot: claude-opus-4-8-high, Reasoning: high, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 1,396 published pairwise votes.Mistral Large 3: Arena rating from 807 published pairwise votes.	Higher measured value1,288.42 95% confidence interval: ±16.853The 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
MMLU-ProEconomics Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value91.825 %	85.782 %	Vals AI Source details Data as of: 09/01/2026
LMArena Text, Style ControlCoding Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Text, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Text, style controlClaude Opus 4.8: Arena rating from 18,069 published pairwise votes.Mistral Large 3: Arena rating from 21,177 published pairwise votes.	Winner1,529.229 95% confidence interval: ±5.786The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.	1,470.674 95% confidence interval: ±4.773The 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: 10/15/2026
LMArena Vision, Style ControlDiagram Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterClaude Opus 4.8: Snapshot: claude-opus-4-8, Harness: Arena Vision, style control Mistral Large 3: Snapshot: mistral-large-3, Harness: Arena Vision, style controlClaude Opus 4.8: Arena rating from 4,942 published pairwise votes.Mistral Large 3: Arena rating from 2,169 published pairwise votes.	Winner1,305.338 95% confidence interval: ±9.53The 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
MMLU-ProEngineering Test details Test setup not documented as identicalNo direct winnerVersion: 1Metric: accuracyScoring: Higher is betterClaude Opus 4.8: Compute: max, Temperature: 1, Output limit: 128,000 tokens Mistral Large 3: Temperature: 0.065, Output limit: 256,000 tokens	Higher measured value87.719 %	74.923 %	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: 43b8c5c46830

Claude Opus 4.8

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.

Claude Opus 4.8

Reasoning (requested): high

Current attempt

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: anthropic/claude-opus-4.8
API model reported in response: anthropic/claude-opus-4.8
Reasoning setting: high
Pinned endpoint: Anthropic | anthropic/claude-4.8-opus-20260528
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: 18 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 Claude Opus 4.8 and Mistral Large 3 with other leading models using the same data and benchmark logic.

View the complete LLM comparison

Claude Opus 4.8 vs. Mistral Large 3

Change model selection

General specifications

API pricing compared

Benchmark index compared

Shared benchmarks

Capability profile from matched benchmarks

Our tests

SVG short test

Claude Opus 4.8

Mistral Large 3

Pelican on a bicycle

Winning one benchmark is not an overall verdict

Related LLM comparisons