Mistral AILanguage model
Magistral Small 1.2
Magistral Small 1.2 has no overall index value yet because there are too few independent benchmark results.
PopularityRank 427 of 785
35out of 100same as last month
based on search, usage and attention
Summary
New in Magistral Small 1.2 is the multimodal revision of the 24B reasoning model. It enables longer reasoning. The weights use Apache 2.0.
Magistral Small 1.2 sits alongside Mistral Small 4, which combines reasoning with instruction following, image understanding, and coding. Mistral’s documentation lists 1.2 as deprecated.
All benchmark results
Every published result with its source, test setup and comparison models.
Show all 19 published benchmark results
Page 1 of 2
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.
CritPt v2: Overall (Show measurement, test conditions, and source)
- Source value
- 0.28571428571428603
- Score
- 0.28571428571428603
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- v2
- Category
- reasoning
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- disputed
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Source model ID: artificial-analysis/70152cb0-fb36-4732-a925-89ef40994be1/magistral-small-2509/magistral-small-2509. Source model name: Magistral Small 1.2. Provider reported by source: Mistral. Model snapshot: Magistral Small 1.2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled. Score display: 0.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-critpt-v2:v2:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The full CritPt v2 run covers 70 questions with five repeats. The official grading server reports pass@1.. Tool policy: Python functions, symbolic expressions, and numerical answers; official grading server. Attempts: 70 questions, five repeats per question, pass@1. Reasoning: reasoning enabled
- Context
- This AA source field contains the original CritPt score. The earlier CritPt v2 attribution was incorrect; the value and former label remain as disputed historical evidence.. The source dataset marks this result as disputed. It remains visible as documented evidence, but is not reliable comparative proof.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 44.353741496598595
- Score
- 44.353741496598595
- 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
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. 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/70152cb0-fb36-4732-a925-89ef40994be1/magistral-small-2509/magistral-small-2509. Source model name: Magistral Small 1.2. Provider reported by source: Mistral. Model snapshot: Magistral Small 1.2. 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: reasoning enabled. Score display: 44.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. 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: reasoning enabled
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.. This result is retained as historical evidence and is not interchangeable with current results.
IFBench: Overall (Show measurement, test conditions, and source)
- Source value
- 44.353741496598595
- Score
- 44.353741496598595
- 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
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. 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/70152cb0-fb36-4732-a925-89ef40994be1/magistral-small-2509/magistral-small-2509. Source model name: Magistral Small 1.2. Provider reported by source: Mistral. Model snapshot: Magistral Small 1.2. 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: reasoning enabled. Score display: 44.4%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-ifbench:AA test set: 294 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. 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: reasoning enabled
- Context
- The often cited 58 refers to verifiable out-of-domain constraint types, not the number of questions in AA's test run.
MMMU-Pro: Overall (Show measurement, test conditions, and source)
- Source value
- 55.4913294797688
- Score
- 55.4913294797688
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- AA cohort: 1,730 questions
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- superseded
- Retrieved at
- 2026-11-02
- Methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/70152cb0-fb36-4732-a925-89ef40994be1/magistral-small-2509/magistral-small-2509. Source model name: Magistral Small 1.2. Provider reported by source: Mistral. Model snapshot: Magistral Small 1.2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Score display: 55.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-02-67d46be20a5b. Source payload hash: 67d46be20a5b412db6cfb60ad190441fcaa5513500b8fd47d033168d0e97b6b2. Parser version: artificial-analysis-rsc-models-v3. Imported at: 2026-11-02. Source cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). AA source value for average reasoning tokens before the answer: 2000. Its methodology averages 60 varied prompts and assumes 2,000 when no average is available. This is not a token cap. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled
- Context
- The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.. This result is retained as historical evidence and is not interchangeable with current results.
MMMU-Pro: Overall (Show measurement, test conditions, and source)
- Source value
- 55.4913294797688
- Score
- 55.4913294797688
- Metric
- pass@1 accuracy
- Unit
- %
- Benchmark version
- AA cohort: 1,730 questions
- Category
- multimodal
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-11-07
- Methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Source model ID: artificial-analysis/70152cb0-fb36-4732-a925-89ef40994be1/magistral-small-2509/magistral-small-2509. Source model name: Magistral Small 1.2. Provider reported by source: Mistral. Model snapshot: Magistral Small 1.2. Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled. Score display: 55.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-11-07-b96e3ffc8c5b. Source payload hash: b96e3ffc8c5b052aa56f96d05e89d02b8cc234a75085820fca0ca2a39e498274. Parser version: artificial-analysis-rsc-models-v4. Imported at: 2026-11-07. Source cohort: artificial-analysis-mmmu-pro:AA cohort: 1,730 questions:standalone:reasoning:effort=unspecified:suffix=unspecified
- Comparison methodology
- Exact AA configuration: Magistral Small 1.2 (release magistral-small-2509, row magistral-small-2509, UUID 70152cb0-fb36-4732-a925-89ef40994be1, reasoning=true, effort=not specified, suffix=not specified). This source capture does not provide an average reasoning-token count. The AA run covers 1,730 questions with ten answer options. Answers are extracted by regex and scored pass@1.. Tool policy: Ten-option multiple choice; regex answer extraction. Attempts: pass@1, one run per question. Reasoning: reasoning enabled
- Context
- The benchmark page describes 3,460 questions in the full MMMU-Pro dataset; AA's methodology specifies a 1,730-question run.
AIME 2024 (Show measurement, test conditions, and source)
- Source value
- 86.14
- Score
- 86.14
- Metric
- pass@1
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Magistral Small 1.2 model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Magistral Small 1.2 row; the card does not report sampling or reasoning-effort settings.
AIME 2025 (Show measurement, test conditions, and source)
- Source value
- 77.34
- Score
- 77.34
- Metric
- pass@1
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Magistral Small 1.2 model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Magistral Small 1.2 row; the card does not report sampling or reasoning-effort settings.
GPQA Diamond (Show measurement, test conditions, and source)
- Source value
- 70.07
- Score
- 70.07
- Metric
- score as published
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Magistral Small 1.2 model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Magistral Small 1.2 row; the card does not report sampling or reasoning-effort settings.
LiveCodeBench (Show measurement, test conditions, and source)
- Source value
- 70.88
- Score
- 70.88
- Metric
- score as published
- Unit
- %
- Benchmark version
- v5
- Category
- coding
- Direction
- Higher is better
- Source type
- vendor-reported
- Evaluator
- Mistral AI Magistral Small 1.2 model card
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Vendor-reported result. Exact Magistral Small 1.2 row; the card labels LiveCodeBench version 5 but not sampling settings.
GPQA Diamond (Show measurement, test conditions, and source)
- Source value
- 58.33
- Score
- 58.33
- Metric
- Accuracy
- Unit
- %
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Vals AI GPQA Diamond leaderboard
- Status
- archived
- Retrieved at
- 2026-10-22
- Methodology
- Independent evaluation. Vals AI reports 58.33% for the exact Magistral Small 1.2 (09/2025) row. Its method uses the 198-question Diamond subset and describes zero-shot and few-shot CoT prompts, but does not identify which prompt variant produced this leaderboard value.
- Context
- The profile already contains a separate Mistral-card GPQA Diamond result of 70.07%. This is a separately sourced Vals evaluation, not a replacement; the prompt and reasoning settings are not matched. Vals marks the benchmark archived. The Vals model overview reports ±2.49 as a standard error, not a confidence interval. A metric-specific N and confidence interval are not reported.
MortgageTax (Show measurement, test conditions, and source)
- Source value
- 62.12
- Score
- 62.12
- Metric
- Accuracy
- Unit
- %
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Vals AI MortgageTax leaderboard
- Status
- archived
- Retrieved at
- 2026-10-22
- Methodology
- Independent evaluation. Vals AI provides mortgage-tax certificates as images and evaluates semantic and numerical extraction. The reported number uses a held-out test of 938 documents, but the page does not disclose how its two task scores are combined.
- Context
- The benchmark is marked archived. The 938 documents are the held-out dataset size, not a demonstrated per-cell sample count for aggregate accuracy; no measurement date or row-specific provider parameters are published. The Vals model overview reports ±0.95 as a standard error, not a confidence interval. A metric-specific N and confidence interval are not reported.
MMLU Pro (Show measurement, test conditions, and source)
- Source value
- 62.13
- Score
- 62.13
- Metric
- Accuracy
- Unit
- %
- Direction
- Higher is better
- Source type
- independent-evaluator
- Evaluator
- Vals AI MMLU Pro leaderboard
- Status
- archived
- Retrieved at
- 2026-10-22
- Methodology
- Independent evaluation. Vals AI states that all reported MMLU Pro results use 5-shot chain-of-thought prompting, with five examples per category. The captured page does not state a model-specific provider configuration or exact test-set sample count.
- Context
- The page is marked archived and was updated on 2026-09-01. That update date is not a measurement date; no exact per-model N is included. The Vals model overview reports ±0.45 as a standard error, not a confidence interval. A metric-specific N and confidence interval are not reported.
Page 1 of 2
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 101 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 8, 2026
Magistral Small 1.2Llama 3.1 Nemotron 70B Instruct 35MiMo-V2.5-Pro 35Mistral Large 2407 35Command A 35
Method changes in the timeline, a jump at these points is no market event:
- 1November 1, 2026: Value only with search or usage data, 30-day attention
- 2November 1, 2026: Method version 4 (common scale, shrinkage)
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
Similar models
More models of the same kind as Magistral Small 1.2, chosen by model line, developer, size, price and release date.
- Magistral SmallMistral AI · same developer
- Devstral SmallMistral AI · same developer
- Devstral Small 2Mistral AI · same developer
- Voxtral Small 24BMistral AI · same developer
- Voxtral Small (latest)Mistral AI · same developer
- Ministral 3 14BMistral AI · same developer
- Codestral-22B-v0.1Mistral AI · same developer
- Codestral (latest)Mistral AI · same developer
All specifications
Architecture
Input and output
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
Frequently asked questions about Magistral Small 1.2
How large is the context window of Magistral Small 1.2?
131,072 tokens. That is how much text Magistral Small 1.2 reads at once, about 200 A4 pages.
Page count as a rule of thumb from Artificial Analysis
GLM-5.1200K
DeepSeek-V3 0324164K
Magistral Small 1.2Rank 94 of 103131K
GLM-4.5131K
GPT OSS 120B131K
DeepSeek-V3.2128K
DeepSeek-R1128K
Can I run Magistral Small 1.2 locally?
Yes, the weights are open.
Stated by Mistral AI
- Open weights
- yes
- License
- Apache 2.0
- Parameters
- 24B
- active per token
- n/a
Sources and data date
Show all 22 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 3 | 0 | 3 |
| Vals AI | 1 | 0 | 1 |
Without vendor claims and historical or disputed results; those stay labelled in the single values.