geekradar
Int
Explore GeekRadar

More to explore

Good gear All topics About us Say hello
GeekRadar / The comparison desk
COMPARE.
AI models
mistral

Mistral Large 2.1

AI model Released

Context window
131,072 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 Large 2.1 1265.3 mistral-large-2411 · 95% interval 1260.8–1269.7 · 28,073 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 Large 2.1

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 Large 2.1 51.3*% Approx. 95% interval: 46.1–56.6% · 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 Large 2.1 Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

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

Mistral Large 2.1 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 Large 2.1 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 Large 2.1

1,238.96 rating

Confidence interval: 1,225.43 – 1,252.49

1914 votes

Category
chinese
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,275.27 rating

Confidence interval: 1,266.45 – 1,284.10

4212 votes

Category
coding
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,241.69 rating

Confidence interval: 1,232.67 – 1,250.70

4439 votes

Category
creative_writing
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,283.88 rating

Confidence interval: 1,278.47 – 1,289.28

16289 votes

Category
english
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,179.27 rating

Confidence interval: 1,172.44 – 1,186.09

18034 votes

Category
exclude_ties
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,207.75 rating

Confidence interval: 1,192.87 – 1,222.63

1510 votes

Category
expert
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,324.97 rating

Confidence interval: 1,284.12 – 1,365.82

204 votes

Category
french
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,241.81 rating

Confidence interval: 1,219.15 – 1,264.46

648 votes

Category
german
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,256.62 rating

Confidence interval: 1,249.63 – 1,263.61

6954 votes

Category
hard_prompts
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,267.57 rating

Confidence interval: 1,259.00 – 1,276.14

4452 votes

Category
hard_prompts_english
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,238.05 rating

Confidence interval: 1,227.34 – 1,248.75

3021 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,230.48 rating

Confidence interval: 1,222.18 – 1,238.78

5130 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,274.62 rating

Confidence interval: 1,259.60 – 1,289.65

1593 votes

Category
industry_legal_and_government
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,260.23 rating

Confidence interval: 1,251.51 – 1,268.96

4869 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,257.19 rating

Confidence interval: 1,247.12 – 1,267.26

3037 votes

Category
industry_mathematical
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,254.62 rating

Confidence interval: 1,237.91 – 1,271.34

1230 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,274.06 rating

Confidence interval: 1,266.77 – 1,281.35

6815 votes

Category
industry_software_and_it_services
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,260.46 rating

Confidence interval: 1,253.31 – 1,267.60

7416 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,248.64 rating

Confidence interval: 1,242.59 – 1,254.69

10971 votes

Category
instruction_following
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,170.06 rating

Confidence interval: 1,147.32 – 1,192.80

629 votes

Category
japanese
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,201.70 rating

Confidence interval: 1,171.77 – 1,231.62

408 votes

Category
korean
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,261.25 rating

Confidence interval: 1,251.71 – 1,270.79

3607 votes

Category
longer_query
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,261.08 rating

Confidence interval: 1,251.76 – 1,270.40

3574 votes

Category
math
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,259.57 rating

Confidence interval: 1,250.58 – 1,268.56

4438 votes

Category
multi_turn
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,235.24 rating

Confidence interval: 1,229.37 – 1,241.10

11784 votes

Category
non_english
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,265.28 rating

Confidence interval: 1,260.85 – 1,269.72

28073 votes

Category
overall
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,251.55 rating

Confidence interval: 1,241.47 – 1,261.63

3258 votes

Category
russian
Evaluated configuration
mistral-large-2411
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

Mistral Large 2.1

1,267.90 rating

Confidence interval: 1,222.48 – 1,313.31

153 votes

Category
spanish
Evaluated configuration
mistral-large-2411
Evaluation type
human preference

Run it locally

Inference · memory estimate

Mistral Large 2.1

Not enough verified architecture information for a reliable VRAM estimate.

API cost

USD / month

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

Mistral Large 2.1

Capabilities

Context window
131,072 tokens
Maximum output
16,384 tokens
Reasoning
No
Tool calling
Yes
Open weights
Yes
Knowledge cutoff
2024-11
Model license
MRL

Input modalities

  • text

Output modalities

  • text

* Provisional data