Skip to main content

OpenAIMistral AILLM matchup

GPT-5.4 minivs.Mistral Large 3

Which one is better?

GPT-5.4 mini performs better than Mistral Large 3, but costs 1.5 times (input) and 3 times (output) as much.

GPT-5.4 mini ahead
IntelligenceOverall index, 100 points = average
75.1

GPT-5.4 mini

Rank 62

32.7

Mistral Large 3

Rank 95

GPT-5.4 mini faster
SpeedTokens per second
97

GPT-5.4 mini

60

Mistral Large 3

Mistral Large 3 cheaper
Price$ per 1M tokens
$1.69

GPT-5.4 mini

$0.75

Mistral Large 3

Popularity0 to 100
n/a

GPT-5.4 mini

48

Mistral Large 3

Rank 145 of 508

Choose GPT-5.4 mini for

GeneralCodingMultimodalFinance

No clear advantage for Mistral Large 3.

Where is the difference?

Strengths at a glance

GPT-5.4 miniMistral Large 3Median of all ranked models

45658510525CodingGPT-5.4 miniGeneralGPT-5.4 miniMultimodalGPT-5.4 miniFinanceGPT-5.4 mini
CodingGPT-5.4 mini ahead
GPT-5.4 mini75.7Rank 71
Mistral Large 331.9Rank 113
Median of ranked models87.5

95 % range: GPT-5.4 mini 70.9 to 80.5, Mistral Large 3 19.3 to 44.5.

AreaGPT-5.4 miniMistral Large 3

The same values and verdicts as the bars below. In the close-up the net starts at 25 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Reasoning, Mathematics, Knowledge, Agents, Legal, Health.

GPT-5.4 mini is ahead in 4 of 10 areas, Mistral Large 3 in none.

GPT-5.4 mini ahead: 4too little data: 6

Areas in the overall index
GeneralGPT-5.4 mini +4679.3 to 33.4
CodingGPT-5.4 mini +4475.7 to 31.9
MultimodalGPT-5.4 mini +4275.1 to 32.8
Agentstoo little data78.7 to 34.3
Reasoningtoo little data72.9 to 34.3
Knowledgetoo little data73.8 to 38.4
Mathematicsonly Mistral Large 3 has a score
Specialist fields
FinanceGPT-5.4 mini +3475.1 to 41.3
Legaltoo little data71.3 to 39.7
Healthonly Mistral Large 3 has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

GPT-5.4 mini vs. Mistral Large 3 at the same effort

Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.

noneGPT-5.4 mini ahead
9.4 points gap across 3 shared test series
Overall index (xhigh vs. none)GPT-5.4 mini ahead
GPT-5.4 mini 75.1 vs. Mistral Large 3 32.7

The gap compares only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeGPT-5.4 miniCoding 75.7 to 31.9
Maths and data analysisopenMathematics without a score for GPT-5.4 mini, Reasoning 72.9 to 34.3 (too little data)
Facts and researchopenKnowledge 73.8 to 38.4 (too little data)
Agents and workflowsopenAgents 78.7 to 34.3 (too little data)
Fast chat repliesGPT-5.4 mini97 to 60 tokens per second
Many requests on a small budgetMistral Large 3$1.69 to $0.75 per 1M tokens
Finance, legal and medical textsGPT-5.4 miniFinance 75.1 to 41.3, Legal 71.3 to 39.7 (too little data), Health without a score for GPT-5.4 mini
Images, screenshots and PDFsGPT-5.4 miniMultimodal 75.1 to 32.8

GPT-5.4 mini vs. Mistral Large 3 in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

GPT-5.4 mini

GPT-5.4 mini: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 2, 2026 · 14 s · $0.01

Test details
Run date
Oct 2, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4-mini
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,142 tokens
Cost of the attempt
$0.0142
Response time
13.5 s
API model reported in response
openai/gpt-5.4-mini
Pinned endpoint
OpenAI | openai/gpt-5.4-mini-20260317
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

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

Earlier attempts (2)

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

Mistral Large 3

Mistral Large 3: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 1, 2026 · 14 s · $0.0022

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
mistralai/mistral-large-2512
Reasoning setting
not specified
Token limit including reasoning
8,192 tokens
Output tokens
1,451 tokens
Cost of the attempt
$0.0022
Response time
14.2 s
API model reported in response
mistralai/mistral-large-2512
Pinned endpoint
Mistral | mistralai/mistral-large-2512
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Reasoning (model default)
no reasoning mode Source

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

Earlier attempts (1)

  • Sep 7, 2026API request failedReasoning setting: not specified
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

GPT-5.4 mini

Unavailable in this round

Mistral Large 3

API request failed. The model was not evaluated.

GPT-5.4 mini and Mistral Large 3 in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
GPT-5.4 minixhigh75.1
Mistral Large 3none32.7

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

GPT-5.4 mini has no popularity score yet.

Over time

Weekly values from October 18, 2026 to November 16, 2026

GPT-5.4 miniMistral Large 3

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricGPT-5.4 miniMistral Large 3
Intelligence
Overall indexpoints, 100 = reference group average, higher is better75.132.7
RankRank 62 of 95Rank 95 of 95
Price per 1M tokens
Inputwhat you send$0.75$0.50
Outputwhat the model writes$4.50$1.50
Cost per task (own tests)average of 1 original-protocol task both models passed (SVG short test not included)$0.014$0.002
Speed
Tokens per second9760
Popularity
Popularitysearch, usage and mentions, 0 to 100n/a48Rank 145 of 508
Technical
Context windowhow much text the model reads at once400,000 tokens≈ 600 A4 pages262,144 tokens≈ 390 A4 pages
Knowledge cutoffAug 31, 2025n/a
ReleasedMar 17, 2026Dec 2, 2025
AvailabilityActiveActive
Open weightsnoyes

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Cheaper than Mistral Large 3Muse Ember 1.0

Overall index 110.5, rank 14$0.10 input and $0.50 output per 1M tokens

View profile
Best model in the overall indexClaude Fable 5.2

Overall index 130.9, rank 1$8 input and $40 output per 1M tokens

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: GPT-5.4 miniB: Mistral Large 3

CorpFin v2Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 60.9%Mistral Large 3: 61.0%Vals AIAs of 08/12/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 83.1%Mistral Large 3: 68.4%Vals AIAs of 09/01/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 81.5%Mistral Large 3: 55.3%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,398Mistral Large 3: 1,231LMArenaAs of 11/15/2026
LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,447Mistral Large 3: 1,415LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,250Mistral Large 3: 1,200LMArenaAs of 11/09/2026
MMLU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.6%Mistral Large 3: 79.8%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.2%Mistral Large 3: 66.2%Vals AIAs of 09/01/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 63.5%Mistral Large 3: 52.1%Vals AIAs of 09/01/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 73.0%Mistral Large 3: 41.4%Vals AIAs of 09/01/2026
Show 54 more benchmarks
TaxEval v2Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 71.2%Mistral Large 3: 73.1%Vals AIAs of 09/01/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.5%Mistral Large 3: 59.8%Vals AIAs of 08/12/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.8%Mistral Large 3: 64.1%Vals AIAs of 09/01/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalGPT-5.4 mini: 97.8%Mistral Large 3: 95.3%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,420Mistral Large 3: 1,239LMArenaAs of 11/15/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,459Mistral Large 3: 1,411LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,285Mistral Large 3: 1,219LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalGPT-5.4 mini: 91.4%Mistral Large 3: 88.6%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.4%Mistral Large 3: 50.0%Vals AIAs of 09/01/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalGPT-5.4 mini: 85.6%Mistral Large 3: 56.2%Vals AIAs of 09/01/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalGPT-5.4 mini: 63.0%Mistral Large 3: 61.6%Vals AIAs of 09/01/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.0%Mistral Large 3: 63.8%Vals AIAs of 08/12/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4 mini: 81.3%Mistral Large 3: 72.7%Vals AIAs of 09/01/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.7%Mistral Large 3: 17.1%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,398Mistral Large 3: 1,231LMArenaAs of 11/15/2026
LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,473Mistral Large 3: 1,431LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,225Mistral Large 3: 1,198LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalGPT-5.4 mini: 89.7%Mistral Large 3: 84.7%Vals AIAs of 09/01/2026
MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identicalGPT-5.4 mini: 47.6%Mistral Large 3: 54.2%Vals AIAs of 09/01/2026
SWE-bench Verified>4 hours · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0.0%Mistral Large 3: 33.3%Vals AIAs of 09/01/2026
TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.4%Mistral Large 3: 84.5%Vals AIAs of 09/01/2026
CorpFin v2Shared Max Context · higher is betterTest setup not documented as identicalGPT-5.4 mini: 60.3%Mistral Large 3: 59.6%Vals AIAs of 08/12/2026
LiveCodeBenchMedium · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.9%Mistral Large 3: 53.5%Vals AIAs of 09/01/2026
LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,495Mistral Large 3: 1,471LMArenaAs of 11/11/2026
LMArena Vision, Style ControlDiagram understanding · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,283Mistral Large 3: 1,233LMArenaAs of 11/09/2026
MMLU ProChemistry · higher is betterTest setup not documented as identicalGPT-5.4 mini: 89.1%Mistral Large 3: 85.0%Vals AIAs of 09/01/2026
SWE-bench Verified1-4 hours · higher is betterTest setup not documented as identicalGPT-5.4 mini: 33.3%Mistral Large 3: 4.8%Vals AIAs of 09/01/2026
LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,401Mistral Large 3: 1,375LMArenaAs of 11/11/2026
LMArena Vision, Style ControlEnglish · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,247Mistral Large 3: 1,208LMArenaAs of 11/09/2026
MMLU ProComputer Science · higher is betterTest setup not documented as identicalGPT-5.4 mini: 87.1%Mistral Large 3: 83.2%Vals AIAs of 09/01/2026
SWE-bench Verified15 min - 1 hour · higher is betterTest setup not documented as identicalGPT-5.4 mini: 70.9%Mistral Large 3: 36.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,450Mistral Large 3: 1,427LMArenaAs of 11/11/2026
LMArena Vision, Style ControlHomework · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,291Mistral Large 3: 1,203LMArenaAs of 11/09/2026
MMLU ProEconomics · higher is betterTest setup not documented as identicalGPT-5.4 mini: 88.7%Mistral Large 3: 85.8%Vals AIAs of 09/01/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,408Mistral Large 3: 1,373LMArenaAs of 11/11/2026
LMArena Vision, Style ControlHumor · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,239Mistral Large 3: 1,186LMArenaAs of 11/09/2026
MMLU ProEngineering · higher is betterTest setup not documented as identicalGPT-5.4 mini: 82.0%Mistral Large 3: 74.9%Vals AIAs of 09/01/2026
LMArena Text, Style ControlExcluding ties · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,449Mistral Large 3: 1,402LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOptical character recognition · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,263Mistral Large 3: 1,214LMArenaAs of 11/09/2026
MMLU ProHealth · higher is betterTest setup not documented as identicalGPT-5.4 mini: 80.1%Mistral Large 3: 77.3%Vals AIAs of 09/01/2026
LMArena Text, Style ControlExpert prompts · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,482Mistral Large 3: 1,428LMArenaAs of 11/11/2026
MMLU ProHistory · higher is betterTest setup not documented as identicalGPT-5.4 mini: 75.3%Mistral Large 3: 70.9%Vals AIAs of 09/01/2026
LMArena Text, Style ControlFrench prompts · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,479Mistral Large 3: 1,432LMArenaAs of 11/11/2026
MMLU ProLaw · higher is betterTest setup not documented as identicalGPT-5.4 mini: 70.1%Mistral Large 3: 56.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlGerman prompts · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,444Mistral Large 3: 1,411LMArenaAs of 11/11/2026
MMLU ProMath · higher is betterTest setup not documented as identicalGPT-5.4 mini: 94.4%Mistral Large 3: 88.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlHard prompts · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,469Mistral Large 3: 1,433LMArenaAs of 11/11/2026
MMLU ProOthers · higher is betterTest setup not documented as identicalGPT-5.4 mini: 80.4%Mistral Large 3: 79.2%Vals AIAs of 09/01/2026
LMArena Text, Style ControlHard prompts, English · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,466Mistral Large 3: 1,440LMArenaAs of 11/11/2026
MMLU ProPhilosophy · higher is betterTest setup not documented as identicalGPT-5.4 mini: 80.6%Mistral Large 3: 76.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlInstruction following · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,435Mistral Large 3: 1,403LMArenaAs of 11/11/2026
MMLU ProPhysics · higher is betterTest setup not documented as identicalGPT-5.4 mini: 90.5%Mistral Large 3: 86.4%Vals AIAs of 09/01/2026
LMArena Text, Style ControlJapanese prompts · higher is betterTest setup not documented as identicalGPT-5.4 mini: 1,406Mistral Large 3: 1,380LMArenaAs of 11/11/2026
MMLU ProPsychology · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.2%Mistral Large 3: 80.6%Vals AIAs of 09/01/2026

More comparisons

Compare GPT-5.4 mini and Mistral Large 3 with the models people compare them with most often.

Compare another matchup