NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Mistral Small 3.2 24B
Mistral AI logo

Mistral Small 3.2 24B

by Mistral AI · Released Jun 2025

Open SourceMultimodal
23.8
avg score
Rank #270
Compare
Better than 13% of all models
Context
256K tokens (~128 books)
Input $/1M
$0.09
Output $/1M
$0.25
Type
multimodal
License
Open Source
Benchmarks
4 tested
Data as of
About

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Tested on 4 benchmarks · BenchGecko score 23.8. Top scores: Dtbench (33.1%), GPQA diamond (32.1%), OTIS Mock AIME 2024-2025 (30.2%).

Looking for similar performance at lower cost?
Gemma 3 27B scores 22.7 (95% as good) at $0.08/1M input · 15% cheaper
Capabilities
math
30.2
#189 globally
knowledge
16.0
#275 globally
general
33.1
#113 globally
Benchmark Scores
Compare All
Tested on 4 benchmarks · Ranked across 3 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
mathCompare math →
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

30.2·
knowledgeCompare knowledge →
GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

32.1·
Chess Puzzles

Tactical chess puzzles testing pattern recognition and multi-move calculation. Measures strategic reasoning ability.

0.0·
generalCompare general →
Dtbench
33.1·
Quick compare:Alibaba logovs Qwen2 1.5B InstructMistral AI logovs Mixtral 8x22B InstructAnthropic logovs Claude 3.5 Haiku
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Mistral AI Mistral Small
Jan 2025
20.4
$0.05/M in33Kctx5 benchmarks
Mar 2025
22.7+2.3
$0.35/M in(+0.30)128Kctx(+95K)10 benchmarks
Mar 2025
$0.00/M in(-0.35)128Kctx
Jun 2025
23.8+1.1
$0.09/M in(+0.09)256Kctx(+128K)4 benchmarks
Mar 2026
$0.15/M in(+0.06)262Kctx(+6K)13 benchmarks
Mar 2026
$0.07/M in(-0.07)262Kctx
Dec 2025
$0.10/M in(+0.03)33Kctx(-229K)
See the full Mistral Small family →
Recently Happened
Mistral Small 3.2 24B pricing increased 25%
Sep 16, 2026
Mistral Small 3.2 24B pricing dropped 20%
Aug 22, 2026
Similar Models
Alibaba logo
Qwen2 1.5B Instruct
Alibaba
23.9n/a
Mistral AI logo
Mixtral 8x22B Instruct
Mistral AI
24.3$2.00/1M
Anthropic logo
Claude 3.5 Haiku
Anthropic
24.5n/a
Links
Info
Mistral AIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Mistral AI
Source Code
GitHubHugging Face
BenchGecko API
mistral-small-3-2-24b-instruct
Specifications
  • Typemultimodal
  • Context256K tokens (~128 books)
  • ReleasedJun 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.000
Available On
Mistral AI logoMistral AI$0.09
Categories
mathknowledgegeneral
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba logoQwen2 1.5B Instruct
23.9
Mistral AI logoMixtral 8x22B Instruct
24.3
Anthropic logoClaude 3.5 Haiku
24.5
Alibaba Qwen logoCodeQwen1.5-7B
24.6
Mistral Small 3.2 24B is an open-source multimodal AI model by Mistral AI, released in June 2025. It has an average benchmark score of 23.8. Context window: 256K tokens.

Related Models

Qwen2 1.5B Instruct · AlibabaMixtral 8x22B Instruct · Mistral AIClaude 3.5 Haiku · AnthropicCodeQwen1.5-7B · Alibaba QwenMistral Small 3.1 24B · Mistral AI

Benchmarks

DtbenchGPQA diamondOTIS Mock AIME 2024-2025Chess Puzzles

Related Pages

Mistral AI · ProviderMistral AI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Mistral Small 3.2 24B by Mistral AI. BenchGecko score 23.8, rank 270 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.0938 input · $0.25 output per 1M tokens (as of 2026-10-05).
  • Sold by 4 providers (as of 2026-10-05): DeepInfra (fp8) $0.0750 in / $0.20 out · Parasail (bf16) $0.0900 in / $0.30 out · Venice (fp8) $0.0938 in / $0.25 out · Mistral $0.10 in / $0.30 out. Every provider

How to cite · data as of 2026-10-05

Mistral Small 3.2 24B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/mistral-small-3-2-24b-instruct

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP