Language modelDeprecated

Mistral Small 3

Mistral AI

Released: January 30, 2025
Data date: September 8, 2026
Successor: Mistral Small 3.1

Benchmark-Meta-Score: Unavailable
Fewer than eight test series
Speed: 155.1 tokens/s
Output throughput
Price: No current rate
Historical rates under Costs
Input: Text
Output: Text

What is distinctive about Mistral Small 3 is the low latency of its 24B text model. Mistral reports around 150 tokens per second; the checkpoint handles 32,000 tokens of context and uses Apache 2.0.

Mistral Small 3.1 adds image input and longer context. Small 3 remains text-based, while Mistral’s current overview lists the generation as deprecated.

Specifications and access

Specification	Value and source
Weights	Open weightsSource
Access	LocalSource
Parameters	24BSource
Context window	32,768 tokensSource
Knowledge cutoff	October 1, 2023Source
Notes	Dense 24B model in the small Mistral model familySource
License	Apache-2.0Source
Release	2025-01-30Source
Parameters	24 BSource
Context window	32,768 tokens (Inventory contained 128k; the primary model card explicitly says 32k, so the card is used.)Source
Knowledge cutoff	2023-10-01Source
Input	TextSource
Output	TextSource
Tool calling	YesSource
Structured output	YesSource

Benchmark meta-analysis

Overall and area scores

These Gradually indexes place selected published measurements on a 0 to 100 scale. They are not accuracy percentages and do not guarantee results in your application.

Retrieval dates of the sources used 2026-10-19 - 2026-10-19

Overall index

Not enough independent results for a score yet

An overall score needs at least eight test series.

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Test series: 1
Test families: 1 / 65
Sources: 1
Share of the fixed test panel (informative): 2 %

General

Index below 1 / 100

provisional

Published configurations differ within this comparison cohort. Treat the index as provisional.

Standard error: ± 0.0
95% interval: 0.0 to 0.0
Test series: 1
Test families: 1 / 5
Sources: 1
Share of the fixed test panel (informative): 20 %

Documented method · Included test families and measurements

Method version: benchmark-meta-score-v3

The index includes active measurements from reviewed primary sources when at least five models are compared in the same documented comparison slice across dataset, harness, agent, tools, and trial count. Each benchmark series and evaluator contributes one shared setup slice from the newest capture. When one source and series include several explicitly documented reasoning tiers, the highest documented tier (none through max) is selected, never the best result value. The explicit source label “Non-reasoning” is treated as none. Unknown or ambiguous tiers exclude the model from that series. Within each series, percentages and rates are logit-transformed, other units stay unchanged, and all values are then standardized. A one-factor model then estimates one shared strength per model and, per series, how sharply it separates the models. Area scores move away from that strength only as far as the model's own results in the area support. The overall score weights the core areas at 75% and finance, law and health at 25%. It requires at least eight test series from two sources and three areas. The 0 to 100 scale refers to a fixed reference group of 29 language models whose average sits at 50.

Published model-specific parameters can differ. This is not a controlled experiment; comparisons with such differences are marked provisional.

Unmeasured series are not entered as zero. Where a model has no own results in a core area, its overall strength stands in, and the note “estimated without own results in …” names the area. Fewer test series lead to a larger standard error.

The 95% interval follows from the standard error of 200 recalculations with randomly redrawn test families. It describes how precisely the recorded test series determine the value. It is no prediction for future tasks or for later recalculations with other participants.

The source count is not a count of independent experiments.

OECD handbook on composite indicators

All 1 test families and 1 of 1 raw measurements are listed here. The complete calculation for every model is available in the JSON export.

Test family: IFBench
General · Mean rank percentile of the family: 1.4 / 100
Family weight in the fixed test panel (informative): 2.14 % · Coverage of this test family: 100 %
- Artificial Analysis
  Published configurations differ within this cohort.
  Measurement:
  artificial-analysis-ifbench
  Series weight within the test family:
  100 %
  Nominal contribution to the overall panel:
  2.14 %
  Raw value:
  26.3945578231293 %
  Metric:
  IFBench prompt-level loose accuracy (pass@1)
  Version:
  AA test set: 294 questions
  Participating models:
  70
  Rank percentile within the cohort:
  1.4 %
  Retrieved:
  2026-10-19
  Comparison cohort:
  artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:tokens=0:suffix=unspecified
  Documented comparison setup
  Publication cohort:
  ["artificial-analysis-ifbench","AA test set: 294 questions","aa-model-page-2026-10-19-8a022369738c"]
  Dataset type:
  artificial-analysis-evaluation
  Tool policy:
  Single-turn answer evaluated with the official IFBench source code
  Attempts:
  pass@1, 5 repeats per question
  Setup and model parameters
  Exact AA configuration: Mistral Small 3 (release mistral-small-3, row mistral-small-3, UUID e5dd499f-c330-45ec-9ff0-a99209c82af7, reasoning=false, source reasoning-token configuration budget=0, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning
  Exact AA configuration: Mistral Small 3 (release mistral-small-3, row mistral-small-3, UUID e5dd499f-c330-45ec-9ff0-a99209c82af7, reasoning=false, source reasoning-token configuration budget=0, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/e5dd499f-c330-45ec-9ff0-a99209c82af7/mistral-small-3/mistral-small-3. Source model name: Mistral Small 3. Provider reported by source: Mistral. Model snapshot: Mistral Small 3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Score display: 26.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19

Benchmark sources at a glance

Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.

Evaluator	Test series	Composite indices	Recorded active measurements
Artificial Analysis	1	1	8

Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.

6 measurements from these sources still lack a verified test-family identity and do not increase the test-series count.

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

IFBench: Overall (Show measurement, test conditions, and source)

Source value: 26.3945578231293
Score: 26.3945578231293
Metric: IFBench prompt-level loose accuracy (pass@1)
Unit: %
Benchmark version: AA test set: 294 questions
Category: general
Task: overall
Task label: Overall
Direction: Higher is better
Comparison cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:non-reasoning:tokens=0:suffix=unspecified
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-10-19
Methodology: Exact AA configuration: Mistral Small 3 (release mistral-small-3, row mistral-small-3, UUID e5dd499f-c330-45ec-9ff0-a99209c82af7, reasoning=false, source reasoning-token configuration budget=0, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Source model ID: artificial-analysis/e5dd499f-c330-45ec-9ff0-a99209c82af7/mistral-small-3/mistral-small-3. Source model name: Mistral Small 3. Provider reported by source: Mistral. Model snapshot: Mistral Small 3. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning. Score display: 26.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
Comparison methodology: Exact AA configuration: Mistral Small 3 (release mistral-small-3, row mistral-small-3, UUID e5dd499f-c330-45ec-9ff0-a99209c82af7, reasoning=false, source reasoning-token configuration budget=0, suffix=not specified). This configured value is not measured token consumption. Artificial Analysis runs 294 questions from the IFBench test set with five repeats per question. The official evaluator scores prompt-level accuracy in loose mode as pass@1.. Tool policy: Single-turn answer evaluated with the official IFBench source code. Attempts: pass@1, 5 repeats per question. Reasoning: non-reasoning
Context: The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.

Source Artificial Analysis

WildBench (Show measurement, test conditions, and source)

Source value: 52.27
Score: 52.27
Metric: percent
Unit: %
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; Public model-card table; judge/config not stated

Source Mistral Small 3 model card

MMLU Pro (Show measurement, test conditions, and source)

Source value: 0.663
Score: 0.663
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact shot count not stated

Source Mistral Small 3 model card

GPQA Main (Show measurement, test conditions, and source)

Source value: 0.453
Score: 0.453
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact shot count not stated

Source Mistral Small 3 model card

HumanEval (Show measurement, test conditions, and source)

Source value: 0.848
Score: 0.848
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact pass@1 setup not stated

Source Mistral Small 3 model card

MATH (Show measurement, test conditions, and source)

Source value: 0.706
Score: 0.706
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact setup not stated

Source Mistral Small 3 model card

MTBench (Show measurement, test conditions, and source)

Source value: 8.35
Score: 8.35
Metric: rating
Unit: rating
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; Public model-card table; judge/config not stated

Source Mistral Small 3 model card

Arena Hard (Show measurement, test conditions, and source)

Source value: 0.873
Score: 0.873
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact normalization not stated

Source Mistral Small 3 model card

IFEval (Show measurement, test conditions, and source)

Source value: 0.829
Score: 0.829
Metric: ratio
Unit: ratio
Direction: Higher is better
Source type: vendor-reported
Evaluator: Mistral Small 3 model card
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. Instruct table; RawFraction [0,1]; Public model-card table; exact setup not stated

Source Mistral Small 3 model card

Artificial Analysis Intelligence Index (Show measurement, test conditions, and source)

Source value: 6.67120856746569
Score: 6.67120856746569
Metric: points
Unit: points
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown

Source Artificial Analysis

Output speed (Show measurement, test conditions, and source)

Source value: 155.125272483902
Score: 155.125272483902
Metric: tokens/s
Unit: tokens/s
Direction: Higher is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Latency reasoning time (Show measurement, test conditions, and source)

Source value: 0
Score: 0
Metric: seconds
Unit: seconds
Direction: Lower is better
Source type: independent-evaluator
Evaluator: Artificial Analysis
Status: active
Retrieved at: 2026-09-08
Methodology: Independent evaluation. unknown; default 10K-input workload only
Context: Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: first-party API. Deprecated model. Artificial Analysis only continues benchmarking the default 10K-input workload.

Source Artificial Analysis

Page 1 of 2

Predecessor and successor

Sources and data date

Type	Evidence and data date
Speed	Mistral. Output speed after the first streaming chunk, not total response time. Classified as deprecated by Artificial Analysis. Artificial Analysis maintains only the default 10K-input workload there. Retrieved September 8, 2026. Source: Artificial Analysis · Artificial Analysis (retrieved September 8, 2026)Speed measurement methodology
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Mistral Small 3 model card · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · Mistral Small 3 model card · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Unresolved	context-discrepancy Original wording Inventory says 128k while the official card says 32k; retain the card value and flag for alias/data review.
Not found in the inspected sources	training-tokens Original wording No token count found.
Not found in the inspected sources	max-output-tokens Original wording No model-specific maximum output found.
Additional source	Context window data
Additional source	Knowledge cutoff data
Additional source	API pricing
Additional source	Artificial Analysis (retrieved October 19, 2026)
Additional source	Model metadata (retrieved September 8, 2026) · Mistral Small 3 announcement · Editorial description reviewed October 2, 2026
Additional source	Mistral model overview · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Ollama: cumulative downloads for the popularity index
Additional source	Replicate: cumulative runs for the popularity index
Additional source	Google Trending Now: limited feed selection for Germany and the US
Additional source	Creative Commons Attribution 4.0
Additional source	Mistral AI, "Mistral Small 3.1" (2026-09-19)

Mistral Small 3

Specifications and access

Overall and area scores

Overall index

General

Test family: IFBench

Benchmark sources at a glance

Measurements without matching peer values

Our tests

SVG short test

Mistral Small 3

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date