Mistral: Mistral Small 3.2 24B

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 releas…

mistralai/mistral-small-3.2-24b-instruct-2506

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 WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.

It supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).

Specifications & capabilities

Input
image, text
Output
text
Context window · tokens
256000
Knowledge cutoff
2023-10-31
Published model ID
Mistral-Small-3.2-24B-Instruct-2506
Capabilities
multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

1–4 / 4

LLM Stats · GitHub archive

0.929

source id
llmStatsArchive
leaderboard name
HumanEval Plus · Raw
dimension
general
metric
HumanEval Plus · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
HumanEval Plus
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • code
created_at
2025-08-03T22:06:10.921756+00:00
paper_link
https://arxiv.org/abs/2305.01210
updated_at
2025-08-03T22:06:10.921756+00:00
description
Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code
benchmark_id
humaneval-plus
multilingual
false
analysis_method
Pass@5
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
HumanEval Plus · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/mistral/models/mistral-small-3.2-24b-instruct-2506/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
mistral/mistral-small-3.2-24b-instruct-2506
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
mistral-small-3.2-24b-instruct-2506
Original result ↗

LLM Stats · GitHub archive

0.929

source id
llmStatsArchive
leaderboard name
HumanEval Plus · Normalized (reported)
dimension
general
metric
HumanEval Plus · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
HumanEval Plus
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • code
created_at
2025-08-03T22:06:10.921756+00:00
paper_link
https://arxiv.org/abs/2305.01210
updated_at
2025-08-03T22:06:10.921756+00:00
description
Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code functional correctness, detecting previously undetected wrong code
benchmark_id
humaneval-plus
multilingual
false
analysis_method
Pass@5
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
HumanEval Plus · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/mistral/models/mistral-small-3.2-24b-instruct-2506/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
mistral/mistral-small-3.2-24b-instruct-2506
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
mistral-small-3.2-24b-instruct-2506
Original result ↗

LLM Stats · GitHub archive

0.783

source id
llmStatsArchive
leaderboard name
MBPP Plus · Normalized (reported)
dimension
general
metric
MBPP Plus · Normalized (reported)
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MBPP Plus
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • code
created_at
2025-08-03T22:06:11.143382+00:00
paper_link
https://arxiv.org/abs/2108.07732
updated_at
2025-08-03T22:06:11.143382+00:00
description
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases for more rigorous evaluation.
benchmark_id
mbpp-plus
multilingual
false
analysis_method
Pass@5
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MBPP Plus · Normalized (reported)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/mistral/models/mistral-small-3.2-24b-instruct-2506/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
mistral/mistral-small-3.2-24b-instruct-2506
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
mistral-small-3.2-24b-instruct-2506
Original result ↗

LLM Stats · GitHub archive

0.783

source id
llmStatsArchive
leaderboard name
MBPP Plus · Raw
dimension
general
metric
MBPP Plus · Raw
rank
1
aggregation scope
status
archived
license
CC-BY-4.0
direction
higherIsBetter
conditions
language
en
benchmark
name
MBPP Plus
language
en
modality
text
verified
false
max_score
1
categories
  • reasoning
  • code
created_at
2025-08-03T22:06:11.143382+00:00
paper_link
https://arxiv.org/abs/2108.07732
updated_at
2025-08-03T22:06:11.143382+00:00
description
MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality. This is an enhanced version with additional test cases for more rigorous evaluation.
benchmark_id
mbpp-plus
multilingual
false
analysis_method
Pass@5
is_self_reported
true
verified_by_llmstats
false
attribution
Jonathan Chavez Tamales and LLM Stats contributors (copyright 2024 jc); TensorTrace structures original results and derives scoped ranks.
license_url
https://creativecommons.org/licenses/by/4.0/
metric_kind
MBPP Plus · Raw
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
data/organizations/mistral/models/mistral-small-3.2-24b-instruct-2506/benchmarks.json
archive_kind
llmStats
evidence_url
https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506
git_revision
872b75f63b8d853c46ed17856424029a0c47b1d2
published_at
2025-10-24T17:47:59Z
snapshot_date
2025-10-24T17:47:59Z
source_revision
6e27aa41f51fa8cb327602349240077d1c7acae9fead8ba2f07db0d549927ddc
publisher_anchor
mistral/mistral-small-3.2-24b-instruct-2506
metric_population
1
current_catalog_url
https://llm-stats.com/
benchmark_evaluation
true
source model id
mistral-small-3.2-24b-instruct-2506
Original result ↗

Published prices

1–5 / 5

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

18 / 100

source id
stanfordFMTI
canonical model id
mistralai/mistral-small-3.2-24b-instruct-2506
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Mistral
assessment type
organization-level disclosure
metric
disclosure_score
result label
18 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Source specification observations

1–3 / 3

openRouter ↗

field
context_length
value
256000
normalized value
256000
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
knowledge_cutoff
reported field
knowledge_cutoff
value
2023-10-31
normalized value
2023-10-31
precision
day
scope
source-model
source id
openRouter
confidence
1

openRouter ↗

field
max_output_tokens
value
26214
normalized value
26214
scope
source-model
source id
openRouter
confidence
1

Original sources

1–8 / 8

Hugging Face · Model reference ↗

DeepInfra · Model page ↗

OpenRouter · Model page ↗

DeepInfra · Catalog ↗

Epoch AI · Catalog ↗

GitHub · Catalog ↗

GitHub · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–6 / 6

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace