Mistral Released October 2026
How Mistral Large 4 Preview compares with the other 88 ranked language models.
Middle of the pack. Ranked #56 of 89 on the overall intelligence score, ahead of 38% of models.
Fast writer. Writes about 90 words per second, faster than 74% of models.
Short wait before answering. You wait about 17 sec before the answer starts.
Cheap to use. $1.05 per million tokens, cheaper than 69% of models.
Good for
No standout strengths in the tests.
Not ideal for
No clear weak spots in the tests.
Intelligence
25
overall score
#56 of 89typical 30
Coding
–
coding score
typical –
Speed
120
tokens per second
#24 of 89typical 91
Wait
17 sec
before it replies
#44 of 79typical 16s
Price
$1.05
per 1M tokens
#27 of 84typical $2.00
Scores on individual tests that make up the intelligence score. The faint line marks the best score of any model.
Humanity's Last Exam
Very hard expert questions across many subjects
SciCode
Writing code to solve science research problems
Long documents
Finding and reasoning over facts in very long texts
Terminal-Bench
Doing real tasks on a computer by itself, like an agent
This model next to the models closest to it. Click another bar to open that model.
Through the API, at the listed price. Chat apps usually charge a monthly plan instead.
1,000 chat replies
a question and a ~350-word answer, 1,000 times
Summarise a 100-page report
about 50,000 words in, a one-page summary out
Write a 2,000-word article
a short brief in, a long article out
Input, per 1M tokens
$0.70
Output, per 1M tokens
$2.10
Median times measured through the API.
1 token is about ¾ of a word. Speeds change with server load, so treat these as typical, not guaranteed.
Other companies' models with the closest intelligence score.
Benchmark data from Artificial Analysis, an independent benchmarking company. Rankings refresh every few hours.
kitio.ai