GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Mistral Large 2407

AI model Released Jul 24, 2024

Context window: 131,072 tokens
Maximum output: 104,857 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 2407 1266.1 mistral-large-2407 · 95% interval 1262.2–1270.0 · 45,459 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 2407

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 Large 2407 49.0^*% Approx. 95% interval: 43.9–54.1% · 2025-01-27 · 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 2407 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 2407 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 2407 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 2407

1,240.34 rating

Confidence interval: 1,229.68 – 1,251.01

3933 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,276.45 rating

Confidence interval: 1,268.65 – 1,284.24

7589 votes

Oct 15, 2026

Category: coding
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,242.68 rating

Confidence interval: 1,234.14 – 1,251.21

6692 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,288.94 rating

Confidence interval: 1,283.85 – 1,294.03

24863 votes

Oct 15, 2026

Category: english
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,185.38 rating

Confidence interval: 1,179.27 – 1,191.48

28276 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,231.98 rating

Confidence interval: 1,219.47 – 1,244.49

2505 votes

Oct 15, 2026

Category: expert
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,273.02 rating

Confidence interval: 1,243.25 – 1,302.78

441 votes

Oct 15, 2026

Category: french
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,253.96 rating

Confidence interval: 1,236.18 – 1,271.74

1230 votes

Oct 15, 2026

Category: german
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,256.34 rating

Confidence interval: 1,250.05 – 1,262.62

12682 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,268.97 rating

Confidence interval: 1,261.32 – 1,276.63

7818 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,225.94 rating

Confidence interval: 1,216.61 – 1,235.28

5167 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,241.54 rating

Confidence interval: 1,233.37 – 1,249.72

7002 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,275.85 rating

Confidence interval: 1,263.52 – 1,288.18

2735 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,266.16 rating

Confidence interval: 1,257.97 – 1,274.34

7485 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,265.36 rating

Confidence interval: 1,256.79 – 1,273.93

5745 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,245.57 rating

Confidence interval: 1,232.18 – 1,258.96

2423 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,276.09 rating

Confidence interval: 1,269.44 – 1,282.73

12143 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,257.87 rating

Confidence interval: 1,251.06 – 1,264.69

12224 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,247.65 rating

Confidence interval: 1,242.00 – 1,253.29

18321 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,187.45 rating

Confidence interval: 1,169.50 – 1,205.39

1249 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,170.03 rating

Confidence interval: 1,145.76 – 1,194.30

751 votes

Oct 15, 2026

Category: korean
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,257.23 rating

Confidence interval: 1,248.62 – 1,265.84

5885 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,261.44 rating

Confidence interval: 1,253.31 – 1,269.56

6664 votes

Oct 15, 2026

Category: math
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,257.28 rating

Confidence interval: 1,249.36 – 1,265.20

8296 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,236.49 rating

Confidence interval: 1,231.20 – 1,241.77

20596 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,266.11 rating

Confidence interval: 1,262.20 – 1,270.01

45459 votes

Oct 15, 2026

Category: overall
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,256.86 rating

Confidence interval: 1,248.09 – 1,265.63

5748 votes

Oct 15, 2026

Category: russian
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

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

Mistral Large 2407

1,236.23 rating

Confidence interval: 1,210.25 – 1,262.20

584 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: mistral-large-2407
Evaluation type: human preference

Run it locally

Inference · memory estimate

Mistral Large 2407

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 Large 2407

Provider offer

Mistral Large 2407 / Pricing tiers 1

Provider / scope	Rate	Currency	Amount / unit
OpenRouterMistral Large 2407Standard	Cached input	USD	0.2 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	6 / 1M tokens

Capabilities

Context window: 131,072 tokens
Maximum output: 104,857 tokens
Reasoning: No
Tool calling: Yes
Open weights: Yes
Knowledge cutoff: 2024-03-31
Model license: Mistral Research

Input modalities

text
pdf

Output modalities

text

* Provisional data