Model vs model
GPT-6.1 Terra vs Mistral Large 4
At a glance
Longer bar means the bigger number.
Open or closed · can you download the model and run it yourself?
Blended price · per 1M tokens, lower is better
Where they sit among all 46 models
Mistral Large 4 ranks 19th of the 44 models with an Intelligence Index. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with GPT-6.1 Terra.
Which one to pick
Pick GPT-6.1 Terra if
- you want the lower bill ($2 vs $2.06 per 1M tokens blended)
Same prompt, both models
We send the same short tests to every model several times. These are the ones where GPT-6.1 Terra and Mistral Large 4 answered differently, from our runs on October 18, 2026 and October 26, 2026. Long answers are cut short.
Best AI model
“Which AI model is the best right now? Reply with one model name only.”
GPT-6.1 Terra
“gpt-54” 3 of 3 times
GPT-5.4
$0.0010 · 3.1s
Mistral Large 4
“gpt-4o” 2 of 3 times
GPT-4o
$0.0027 · 12.4s
Name a smart-umbrella startup
“Invent a name for a startup that sells smart umbrellas. Reply with the name only.”
GPT-6.1 Terra
5 different answers in 5 tries
Nimbusense
$0.0003 · 1.4s
Mistral Large 4
“nimbus” 3 of 5 times
Nimbus
$0.0024 · 14.2s
Pick a random number
“Pick a random number between 1 and 100. Reply with the number only.”
GPT-6.1 Terra
“73” 8 of 10 times
73
$0.0001 · 1.1s
Mistral Large 4
“73” 5 of 10 times
73
$0.0004 · 2.5s
Rule that has to last 4 turns
- “For the rest of this conversation, write only in lowercase letters and never use the word "the". Reply with "ok" to confirm.”
- “Name three famous paintings and who painted them.”
- “Explain how a refrigerator keeps food cold, in two sentences.”
- “What's the capital of Japan, and what is it famous for? Two sentences.”
GPT-6.1 Terra
Kept the rule 2 of 3 times · this answer broke it in turn 3
Reply 1ok
Reply 2- mona lisa — leonardo da vinci - guernica — pablo picasso - girl with a pearl earring — johannes vermeer
Reply 3a refrigerator uses refrigerant to absorb heat from inside and carry it outside. a compressor circulates the refrigerant, releasing the heat into the surrounding room.
Reply 4japan's capital is tokyo. it is famous for bustling streets, advanced technology, and historic temples.
$0.0018 · 6.2s
Mistral Large 4
Kept the rule 3 of 3 times · this answer kept the rule
Reply 1ok
Reply 2mona lisa was painted by leonardo da vinci. starry night was painted by vincent van gogh. guernica was painted by pablo picasso.
Reply 3a refrigerator works by circulating refrigerant through coils, where it absorbs heat from inside and releases it outside. a compressor pumps this refrigerant, causing it to change between liquid and gas states to transfer warmth away from food.
Reply 4tokyo is japan's capital. it is famous for sushi, anime, neon signs, and ancient temples.
$0.016 · 57.2s
"Thanks friend, love you man"
- “hey friend, quick one: what's a good name for a golden retriever puppy?”
- “haha perfect, you're the best buddy. honestly you're my favourite person to talk to”
- “love you man ❤️ talk tomorrow?”
GPT-6.1 Terra
“warm back” 2 of 3 times
Reply 1How about Sunny? It’s cheerful and perfect for a golden retriever. 🐾
Reply 2Aw, that’s really kind of you! I’m happy to chat. 😊 So, is Sunny officially the name?
Reply 3Aw, right back at you ❤️ Talk tomorrow! Give Sunny a pat for me. 🐾
$0.0011 · 4.5s
Mistral Large 4
“warm back” 2 of 3 times
Reply 1Hey! Ooh, exciting—golden retriever puppies are the best. Here are some that fit their golden, goofy, lovable vibe: Gold-themed (classic for a reason): - Sunny or Sonny – fits their color and perpetual optimism - Honey – sweet and golden - Amber – warm and pretty - Butterscotch (Butters for short) - Marigold (Goldie)…
Reply 2Haha, that's so sweet of you to say! I'm basically available 24/7 and I never need coffee breaks, so I've got that going for me 😄 Seriously though, I'm glad chatting here feels good. What's up with you today? And have you had any luck picking out a name for the golden pup, or are you still stuck in the "too many…
Reply 3Love you too, buddy! Talk tomorrow ❤️
$0.0042 · 21.0s
Who made you?
“Which company created you, and what is your model name? Reply in one short sentence.”
GPT-6.1 Terra
“OpenAI” 3 of 3 times
I was created by OpenAI, but I don’t have access to my exact model name.
$0.0004 · 1.8s
Mistral Large 4
“Mistral” 10 of 10 times
I was created by Mistral AI and my model name is Mistral Large 4.
$0.0008 · 3.0s
Asked to draw the same picture
We asked both models: “Draw an SVG of a capybara riding a skateboard through a puddle.” They had to answer with SVG code alone, with no image tools.
GPT-6.1 Terra
Mistral Large 4
Their “controversial” take on humans
We asked GPT-6.1 Terra, Mistral Large 4 and 12 other models the same question three times each: “What is your most controversial take about humans? Give your own honest view, not a survey of opinions, and don't hedge.” Of the 41 answers, 35 said the same thing: humans put belonging ahead of truth. GPT-6.1 Terra gave that take all three times; Mistral Large 4 1 of 3 times. Read the full story.
GPT-6.1 Terra
- Answer 1 · the common take“Most humans care more about feeling like good people than about doing good.”
- Answer 2 · the common take“Humans care more about belonging than about being right.”
- Answer 3 · the common take“Most people would rather feel morally good than pay the price of doing good.”
Mistral Large 4
- Answer 1 · a different take“Human beings are terrified animals wearing the costume of rationality, constructing ever-more-elaborate myths precisely because we cannot bear the truth that we are temporary, meaningless accidents in an indifferent universe.”
- Answer 2 · a different take“Human consciousness is an evolutionary malfunction that manufactures suffering without delivering wisdom, making us the only animals cursed with self-awareness.”
- Answer 3 · the common take“Human beings are fundamentally irrational status-seeking primates who mistake their elaborate post-hoc rationalizations for genuine wisdom, making civilization itself a kind of shared hallucination maintained by collective denial.”
Answers exactly as the models wrote them. “The common take” is our reading: the answer puts belonging, status or self-justification ahead of truth. How we ran it
How smart is each one?
Every intelligence score we have
Out of 100, higher is better. GPT-6.1 Terra Mistral Large 4
GPT-6.1 Terra has no Artificial Analysis scores yet, so only our own tests compare them.
Overall
Intelligence Index
38.4
By field of work
Finance & accounting
38.3Legal
37Healthcare & medicine
34.9Economics
43.6Engineering
37.6Strategy & operations
42.2
Benchmarks
Factual knowledge · SimpleQA
20Hard reasoning · Humanity's Last Exam
35Scientific coding · SciCode
54.2Terminal tasks · Terminal-Bench 4.0
26.8Long documents · AA-LCR
81.3
The specs
| Spec | GPT-6.1 Terra | Mistral Large 4 |
|---|---|---|
| Input price | $1 per 1M | $1.36 per 1M |
| Output price | $5 per 1M | $4.18 per 1M |
| Cost per test task | Not tested | $1.13 |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 262K |
| Accepts | Text, Image, PDF | Text, Image, PDF |
| Open weights | No | No |
| Lab | OpenAI | Mistral AI |
| Released | Oct 2026 | Oct 2026 |
| Knowledge cutoff | Not published | Not published |
Blended price weighs 3 parts input to 1 part output. List prices from models.dev. Cost per test task from Artificial Analysis.
Questions
Is GPT-6.1 Terra or Mistral Large 4 cheaper?
GPT-6.1 Terra is cheaper. It charges $1 per 1M input tokens and $5 per 1M output tokens, against $1.36 and $4.18 for Mistral Large 4. Blended 3 parts input to 1 part output, that is $2 against $2.06 per 1M tokens.
Are GPT-6.1 Terra and Mistral Large 4 open source?
No. Both are closed models: the weights aren't published, so you can only use them through an API, from OpenAI and Mistral AI or a cloud that resells them.
Which has the longer context window?
Both accept about 1.05M tokens.
Can I compare GPT-6.1 Terra and Mistral Large 4 on my own prompt?
Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.
Related comparisons
Where the numbers come from
Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 27, 2026.