Models / Mistral Large 3

Mistral AI

Mistral Large 3

Mistral Large 3 trails most of the field on what it has been measured on; worth a look for simple, high-volume work where cost matters most. The cheapest model of similar intelligence is gpt-oss-20b, at $0.06 per million tokens against $0.75.

Superseded. Mistral Large 4 is Mistral AI's newer model in this line, at $2.06 blended: see Mistral Large 4.

Results 16 Nov 2026 · 27 results · 4 sources

Test Mistral Large 3 on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.50 in · $1.50 out
Mistral AI's list price, 10 Nov 2026 · compare prices$0.05 cached input · 50% off in batch
Speed
Not measured
Intelligence Index
9.3
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Mistral AI, based in France
Weights not published
Released
2 Dec 2025
262,144 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 141st of 185Claude Opus 5.5 – $0.75 blended, 50th percentilecheapest: Mistral Nemo –
Models priced $0.25–1 per million tokens 46th of 61MiMo-V2.6-Pro – sets this group –
Models with similar intelligence sets this group – $0.75 blended, 74th percentilecheapest: gpt-oss-20b –
Models from developers based in the EUall Mistral AI's 4th of 15Mistral Large 4 – $0.75 blended, 53rd percentilecheapest: Mistral Nemo –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $0.25–1 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 136th of 159 available · 40th of 47 at its price
BenchmarkMistral Large 3Rank among availableBest available
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 0.0% 67th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 12.0% 88th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 5.8% 87th of 104 Grok 4.6 50.7%
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 150th of 187 available · 50th of 61 at its price
BenchmarkMistral Large 3Rank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 9.3 141st of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 4.2% 165th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 68.0% 119th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 95th of 169 available · 23rd of 58 at its price
BenchmarkMistral Large 3Rank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,414 87th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 41.6 77th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 115th of 139 available · 27th of 40 at its price
BenchmarkMistral Large 3Rank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 14.5% 64th of 71 GPT-5.4 nano 3.1%
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,434 72nd of 109 Gemini 4 Argon 1,511
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Mistral Large 3 at $0.75 blended, Intelligence Index 9.3. "Similar intelligence" means within 4 points or better.

Where to run it

2 hosts on OpenRouter at the standard service tier, with a median of $0.79 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Mistralnot stated$0.50$1.50$0.75
Mistralnot stated$0.55$1.65$0.82

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Mistral Large 3MiMo-V2.6-Pro
most intelligent at $0.25–1 per million tokens
gpt-oss-20b
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Mistral Large 4
most intelligent from the EU
Price per million tokens $0.75 $0.54$0.06$8.00$2.06
Tokens a second – 432779660
Intelligence Index 9.3 46.310.057.638.4
Spring Prompt overall – ––8225
Rank among available models, by use case
Product listings – ––13th27th
Decks from an analysis – ––7th30th
User surveys – ––4th17th
Marketing planning – ––9th23rd
Agents and tool use 136th of 159 23rd130th3rd37th
Professional work – ––3rd–
Reasoning and knowledge 150th of 187 13th132nd1st54th
Writing 95th of 169 23rd155th5th–
Sticking to the facts 115th of 139 10th–3rd–
Speed under pressure – –––25th

Shaded figures are better than Mistral Large 3's. A dash means no result.

Where it has been measured

46th most intelligent of the 61 models priced $0.25–1 per million tokens. Among models available today, in the bottom quarter for agents and tool use, reasoning and knowledge, and sticking to the facts.

Artificial Analysis lists it but has not published a speed for it yet

Every result

27 published results from 4 sources, each in the source's own units, with the configuration that produced it.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 7 results
MeasureValueRankConfigurationDated
Arena Text factuality: overallArena rating, higher is better 1,434
1,431–1,436
106 of 182 Mistral Large 3 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,410
1,405–1,415
142 of 406 Mistral Large 3 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,374
1,368–1,379
149 of 411 Mistral Large 3 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,427
1,420–1,434
147 of 363 Mistral Large 3 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,400
1,396–1,405
143 of 413 Mistral Large 3 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,414
1,411–1,417
141 of 413 Mistral Large 3 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,389
1,384–1,394
143 of 412 Mistral Large 3 2 Oct 2026

Not shown: Not an error rate: claims that cannot be checked on the web are skipped, and preference still carries most of the weight.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 20.1 158 of 187 Mistral Large 3 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 9.3 331 of 413 Mistral Large 3 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 68.0% 258 of 360 Mistral Large 3 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.2% 374 of 419 Mistral Large 3 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 36.2% 234 of 288 Mistral Large 3 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 36.0% 325 of 407 Mistral Large 3 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 36.6% 177 of 205 Mistral Large 3 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 12.0% 157 of 188 Mistral Large 3 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Mistral Large 3 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 15.9% 170 of 282 Mistral Large 3 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 5.8% 149 of 175 Mistral Large 3 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 24.6% 239 of 286 Mistral Large 3 20 Oct 2026

Not shown: Not your codebase or tools.

UGI Leaderboard · reported by UGI Leaderboard · 6 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 15.0% 127 of 379 Mistral Large 3 (no reasoning) 6 Dec 2025
UGI: requested-length error% off the requested word count, lower is better 23.0% 216 of 379 Mistral Large 3 (thinking reasoning) 6 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.38 75 of 379 Mistral Large 3 (no reasoning) 6 Dec 2025
UGI: style adherencescore from 0 to 1, higher is better 0.37 89 of 379 Mistral Large 3 (thinking reasoning) 6 Dec 2025
UGI: writing scorescore out of 100, higher is better 41.6 210 of 379 Mistral Large 3 (no reasoning) 6 Dec 2025
UGI: writing scorescore out of 100, higher is better 41.5 215 of 379 Mistral Large 3 (thinking reasoning) 6 Dec 2025

Not shown: Not other format limits such as character counts or bullet counts.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 98.8% 72 of 108 Mistral Large 3 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 14.5% 92 of 108 Mistral Large 3 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Will Mistral Large 3 work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.