GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Mistral Small 3.1 24B

AI model Released Mar 17, 2025

Context window: 128,000 tokens
Maximum output: 16,384 tokens
Open weights: Yes

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Mistral Small 3.1 24B 1277.1 mistral-small-3.1-24b-instruct-2503 · 95% interval 1272.6–1281.7 · 32,727 votes · 2026-10-15

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Mistral Small 3.1 24B

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Mistral Small 3.1 24B 47.5^*% Approx. 95% interval: 42.1–52.9% · 2025-03-18 · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Mistral Small 3.1 24B Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Mistral Small 3.1 24B Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Mistral Small 3.1 24B Not available

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,252.59 rating

Confidence interval: 1,239.28 – 1,265.90

2228 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,308.79 rating

Confidence interval: 1,300.91 – 1,316.67

6115 votes

Oct 15, 2026

Category: coding
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,252.21 rating

Confidence interval: 1,242.76 – 1,261.66

4113 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,294.60 rating

Confidence interval: 1,288.76 – 1,300.45

14246 votes

Oct 15, 2026

Category: english
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,203.16 rating

Confidence interval: 1,196.77 – 1,209.54

23339 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,256.97 rating

Confidence interval: 1,241.96 – 1,271.99

1680 votes

Oct 15, 2026

Category: expert
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,272.61 rating

Confidence interval: 1,243.57 – 1,301.65

457 votes

Oct 15, 2026

Category: french
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,266.12 rating

Confidence interval: 1,245.02 – 1,287.22

873 votes

Oct 15, 2026

Category: german
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,277.64 rating

Confidence interval: 1,271.80 – 1,283.49

14625 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,289.59 rating

Confidence interval: 1,281.83 – 1,297.35

6529 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,257.44 rating

Confidence interval: 1,248.81 – 1,266.08

5507 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,250.11 rating

Confidence interval: 1,242.02 – 1,258.20

5819 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,270.15 rating

Confidence interval: 1,257.05 – 1,283.26

2115 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,264.98 rating

Confidence interval: 1,256.20 – 1,273.75

5223 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,271.14 rating

Confidence interval: 1,257.67 – 1,284.62

1934 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,267.13 rating

Confidence interval: 1,252.83 – 1,281.42

1946 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,301.31 rating

Confidence interval: 1,294.91 – 1,307.72

10904 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,268.52 rating

Confidence interval: 1,261.05 – 1,275.99

7059 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,263.07 rating

Confidence interval: 1,255.96 – 1,270.18

8047 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,207.73 rating

Confidence interval: 1,185.81 – 1,229.64

809 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,206.89 rating

Confidence interval: 1,182.99 – 1,230.80

714 votes

Oct 15, 2026

Category: korean
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,298.42 rating

Confidence interval: 1,290.65 – 1,306.20

6343 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,261.18 rating

Confidence interval: 1,248.11 – 1,274.26

2105 votes

Oct 15, 2026

Category: math
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,270.38 rating

Confidence interval: 1,261.76 – 1,278.99

5411 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,254.62 rating

Confidence interval: 1,249.11 – 1,260.13

18470 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,277.13 rating

Confidence interval: 1,272.61 – 1,281.66

32727 votes

Oct 15, 2026

Category: overall
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,241.63 rating

Confidence interval: 1,229.19 – 1,254.06

2795 votes

Oct 15, 2026

Category: polish
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,263.26 rating

Confidence interval: 1,251.44 – 1,275.09

2417 votes

Oct 15, 2026

Category: russian
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

Mistral Small 3.1 24B

1,283.59 rating

Confidence interval: 1,261.80 – 1,305.38

809 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: mistral-small-3.1-24b-instruct-2503
Evaluation type: human preference

Run it locally

Inference · memory estimate

Mistral Small 3.1 24B

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

Mistral Small 3.1 24B

Provider offer

Capabilities

Context window: 128,000 tokens
Maximum output: 16,384 tokens
Reasoning: No
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2024-06
Model license: Apache 2.0

Input modalities

text
image

Output modalities

text

* Provisional data