Ministral 3 8B 2512

Released on 2 December 2025

Compare this model

Lab: Mistral AI (France)
Weights: Open weights
Context window: 262k tokens
Maximum output: 210k tokens
Input / output price: $0.15 / $0.15 per million tokens
Input modalities: Text
Image
Reasoning: No
OpenRouter identifier: mistralai/ministral-8b-2512

At a glance

Updated 8 October 2026

Business Index

71.6%± 6.1 (95% margin of error)

Rank 25 / 27

54.8%100.0%

Average cost per test

$0.0007

5th cheapest of 27

$0.0002$0.058

Median time

1.7 s

3rd fastest of 27

1.5 s29.1 s

Average hallucinations: 0.0%
Benchmarks taken: 2 / 2

Scores by business function

The model's mean accuracy across the benchmarks of each business function.

Accuracy

Finance
43.8%
Accounting
99.3%
Human resources
Not tested
Legal
Not tested
Sales
Not tested
Marketing
Not tested
Customer service
Not tested
Procurement & logistics
Not tested
IT
Not tested
Management
Not tested

Results by benchmark

Finance

Financial report analysis
43.8%± 12.2
rank 25 of 27

Accounting

Advertising invoice extraction
99.3%± 1.2
rank 9 of 27

Bars on a 0 to 100% scale. The rank compares the models tested on the same benchmark.

Stability from run to run

A given model alias can change behaviour without notice; re-testing it at every run is how that drift gets caught.

No benchmark has been published twice with this model yet: there is no curve to draw.