Models / Mistral Small 3.2 24B

Mistral AI

Mistral Small 3.2 24B

Mistral Small 3.2 24B 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 Gemma 3 4B, at $0.04 per million tokens against $0.13.

Results 16 Nov 2026 · 37 results · 4 sources

Test Mistral Small 3.2 24B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$0.09 in · $0.25 out
Typical host on OpenRouter, 10 Nov 2026 · compare prices
Speed
Not measured
Intelligence Index
7.0
Artificial Analysis
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Mistral AI, based in France
Weights published
Released
20 Jun 2025
256,000 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 162nd of 185Claude Opus 5.5 – $0.13 blended, 10th percentilecheapest: Mistral Nemo –
Models priced under $0.25 per million tokens 25th of 41Claude Haiku 5.5 – sets this group –
Models with similar intelligence sets this group – $0.13 blended, 29th percentilecheapest: Gemma 3 4B –
Models from developers based in the EUall Mistral AI's 9th of 15Mistral Large 4 – $0.13 blended, 20th percentilecheapest: Mistral Nemo –
Open-weights models 86th of 104MiMo-V2.6-Pro – $0.13 blended, 15th 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 under $0.25 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 119th of 159 available · 16th of 37 at its price
BenchmarkMistral Small 3.2 24BRank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 37.2% 20th of 36 Claude Opus 4.5 77.5%
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 5.6% 94th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 6.2% 85th of 104 Grok 4.6 50.7%
  • tau2-bench: 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 160th of 187 available · 27th of 41 at its price
BenchmarkMistral Small 3.2 24BRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 7.0 162nd of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 4.3% 161st of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 50.5% 147th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 123rd of 169 available · 12th of 39 at its price
BenchmarkMistral Small 3.2 24BRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,356 116th of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 36.3 88th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers Not measured
  • Vectara Hallucination Leaderboard: has not measured this model.
  • Arena (formerly LMArena): has not measured this model.
  • 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 Small 3.2 24B at $0.13 blended, Intelligence Index 7.0. "Similar intelligence" means within 4 points or better.

Where to run it

4 hosts on OpenRouter at the standard service tier, with a median of $0.14 blended per million tokens; quantisation where the host states it: FP8, BF16. Cheapest first.

HostQuantisationInputOutputBlended
DeepInfraFP8$0.07$0.20$0.11
VeniceFP8$0.09$0.25$0.13
ParasailBF16$0.09$0.30$0.14
Mistralnot stated$0.10$0.30$0.15

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 Small 3.2 24BClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
Gemma 3 4B
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Mistral Large 4
most intelligent from the EU
Price per million tokens $0.13 $0.20$0.04$8.00$2.06
Tokens a second – 240–9660
Intelligence Index 7.0 43.44.857.638.4
Spring Prompt overall – 40–8225
Rank among available models, by use case
Product listings – 20th–13th27th
Decks from an analysis – 18th–7th30th
User surveys – 7th–4th17th
Marketing planning – 30th–9th23rd
Agents and tool use 119th of 159 28th158th3rd37th
Professional work – ––3rd–
Reasoning and knowledge 160th of 187 25th181st1st54th
Writing 123rd of 169 –157th5th–
Sticking to the facts – –32nd3rd–
Speed under pressure – 21st––25th

Shaded figures are better than Mistral Small 3.2 24B's. A dash means no result.

Research and examples

Where it has been measured

25th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the bottom quarter for agents and tool use, and reasoning and knowledge.

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

Every result

37 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) · 6 results
MeasureValueRankConfigurationDated
Arena Text: business, management and financeArena rating, higher is better 1,363
1,352–1,374
203 of 406 Mistral Small 3.2 24B 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,324
1,311–1,337
206 of 411 Mistral Small 3.2 24B 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,334
1,315–1,354
230 of 363 Mistral Small 3.2 24B 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,338
1,329–1,347
218 of 413 Mistral Small 3.2 24B 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,356
1,351–1,362
207 of 413 Mistral Small 3.2 24B 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,329
1,319–1,339
217 of 412 Mistral Small 3.2 24B 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 12 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 12.5 170 of 187 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 7.0 373 of 413 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 50.5% 321 of 360 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 4.3% 369 of 419 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 33.5% 245 of 288 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 20.3% 361 of 407 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 28.6% 195 of 205 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 5.6% 165 of 188 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 0.0% 152 of 204 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 6.8% 215 of 282 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 6.2% 146 of 175 Mistral Small 3.2 24B 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 29.5% 215 of 286 Mistral Small 3.2 24B 20 Oct 2026

Not shown: Not your codebase or tools.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 65.7% 88 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 87.9% 17 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 15.1% 56 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 18.1% 50 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 14.8% 58 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 11.5% 63 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 32.4% 59 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 37.2% 51 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 93.8% 8 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 87.5% 27 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 89.7% 4 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 73.6% 81 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 79.1% 17 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 77.3% 32 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 7.5% 60 of 109 Mistral Small 3.2 24B (bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 31.0% 34 of 109 Mistral Small 3.2 24B (bfcl fc) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

UGI Leaderboard · reported by UGI Leaderboard · 3 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 17.0% 148 of 379 Mistral Small 3.2 24B 6 Sep 2025
UGI: style adherencescore from 0 to 1, higher is better 0.35 193 of 379 Mistral Small 3.2 24B 6 Sep 2025
UGI: writing scorescore out of 100, higher is better 36.3 242 of 379 Mistral Small 3.2 24B 6 Sep 2025

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

Will Mistral Small 3.2 24B 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.