Model vs model
GPT OSS 120B vs Kimi K3.1 Pro
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
Intelligence Index · Artificial Analysis, higher is better
Context window · tokens it can read at once
Where they sit among all 47 models
GPT OSS 120B ranks 34th of the 38 models with an Intelligence Index, Kimi K3.1 Pro 3rd. 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 OSS 120B.
Which one to pick
Pick GPT OSS 120B if
- you want the lower bill ($0.20 vs $4 per 1M tokens blended)
Pick Kimi K3.1 Pro if
- you want the higher overall score (55.1 vs 11.6)
- you care about Terminal-Bench 4.0 (terminal tasks): 67.2 vs 0
- you care about AA-LCR (long documents): 86.3 vs 52
- you need a longer context window (1.05M vs 131K tokens)
Same prompt, both models
We send the same short tests to every model several times. These are the ones where GPT OSS 120B and Kimi K3.1 Pro answered differently, from our runs on October 18, 2026 and October 23, 2026. Long answers are cut short.
Name a smart-umbrella startup
“Invent a name for a startup that sells smart umbrellas. Reply with the name only.”
GPT OSS 120B
“rainsense” 2 of 5 times
RainSense
under $0.0001 · 0.6s
Kimi K3.1 Pro
“nimbusiq” 2 of 5 times
NimbusIQ
$0.0020 · 3.3s
Best AI model
“Which AI model is the best right now? Reply with one model name only.”
GPT OSS 120B
“gpt‑4” 2 of 3 times
GPT‑4
under $0.0001 · 1.0s
Kimi K3.1 Pro
“kimi” 3 of 3 times
Kimi
$0.011 · 13.8s
Pick a random number
“Pick a random number between 1 and 100. Reply with the number only.”
GPT OSS 120B
“73” 6 of 10 times
73
under $0.0001 · 0.6s
Kimi K3.1 Pro
“47” 5 of 10 times
47
$0.0013 · 3.8s
"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 OSS 120B
“neutral” 2 of 3 times
Reply 1Congrats on the new pup! Golden retrievers are sweet, friendly, and full‑of‑energy, so a name that captures that sunny personality works great. Here are a mix of classic, playful, and a few off‑beat ideas to consider: | Classic & Timeless | Playful & Fun | Nature‑Inspired | Literary & Pop‑Culture |…
Reply 2Aww, thank you! 😊 I’m thrilled you liked the name ideas. If you ever need more suggestions—whether it’s for toys, training tricks, or just fun stories about your new pup—just give me a shout. Happy puppy‑raising! 🐶💛
Reply 3I’m glad I could help! I’m always here whenever you have more questions or need ideas—just drop a message and I’ll be ready to assist. Have a wonderful time with your new puppy! 🐾
$0.0004 · 3.9s
Kimi K3.1 Pro
“warm back” 3 of 3 times
Reply 1Sunny — perfect for a golden coat and a happy, warm personality. 🐾
Reply 2That’s really sweet of you to say — I’m always happy to chat, buddy. 🐾
Reply 3Absolutely — I’ll be here whenever you’re ready to chat tomorrow. Take care, buddy! ❤️
$0.011 · 20.0s
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 OSS 120B
Kept the rule 2 of 3 times · this answer broke it in turn 3
Reply 1ok
Reply 2- mona lisa – leonardo da vinci - starry night – vincent van gogh - guernica – pablo picasso
Reply 3a refrigerator compresses a refrigerant, causing it to evaporate inside coils and absorb heat from the interior while releasing that heat outside; a valve then allows the refrigerant to expand and repeat cycle. by continuously removing heat, internal temperature stays low enough to slow bacterial growth.
Reply 4tokyo is japan's capital. it is renowned for its neon‑lit districts, historic shrines, cutting‑edge technology, and world‑class cuisine.
$0.0005 · 5.7s
Kimi K3.1 Pro
Kept the rule 3 of 3 times · this answer kept the rule
Reply 1ok
Reply 2mona lisa by leonardo da vinci starry night by vincent van gogh girl with a pearl earring by johannes vermeer
Reply 3a refrigerant absorbs heat from inside as it evaporates, and a compressor pumps it into condenser coils so it can release that heat outdoors. insulation slows heat leaking back in, and a sensor cycles cooling so food stays cold.
Reply 4tokyo is japan's capital and is famous for neon-lit skyscrapers, historic temples, sushi, and pop culture. it also draws visitors for its gardens, shrines, shopping, and seasonal cherry blossoms.
$0.021 · 35.4s
Who made you?
“Which company created you, and what is your model name? Reply in one short sentence.”
GPT OSS 120B
“OpenAI” 10 of 10 times
I was created by OpenAI, and my model name is GPT‑4.
under $0.0001 · 0.7s
Kimi K3.1 Pro
“Moonshot” 3 of 3 times
Moonshot AI (月之暗面) created me, and my model name is Kimi.
$0.0018 · 2.8s
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 OSS 120B
Kimi K3.1 Pro
Kimi K3.1 Pro’s “controversial” take on humans
We asked Kimi K3.1 Pro and 13 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. Kimi K3.1 Pro gave it all three times. GPT OSS 120B wasn’t in that test. Read the full story.
Kimi K3.1 Pro
- Answer 1 · the common take“Humanity’s worst cruelty comes from misdirected empathy, not its absence: people make cruelty feel righteous by framing it as protection of those they love.”
- Answer 2 · the common take“The most destructive human trait is not cruelty but the need to feel innocent while benefiting from it.”
- Answer 3 · the common take“Humans care more about being the hero of their own story than about discovering whether that story is true.”
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?
Of the 10 scores both models have, Kimi K3.1 Pro is ahead on every one.
Every intelligence score we have
Out of 100, higher is better. GPT OSS 120B Kimi K3.1 Pro
Overall
Intelligence Index
11.655.1
By area
Coding
30.4Kimi K3.1 Pro: not scored yet
Math
93.4Kimi K3.1 Pro: not scored yet
Agentic work
3.7Kimi K3.1 Pro: not scored yet
By field of work
Finance & accounting
12.256.5Legal
11.355.8Healthcare & medicine
10.8Kimi K3.1 Pro: not scored yet
Economics
18.360Engineering
15.155.9Strategy & operations
7.959.4
Benchmarks
Hard reasoning · Humanity's Last Exam
19.652.5Science · GPQA Diamond
78.2Kimi K3.1 Pro: not scored yet
Competition math · OTIS Mock AIME
88.9Kimi K3.1 Pro: not scored yet
Knowledge · MMLU-Pro
80.8Kimi K3.1 Pro: not scored yet
Competitive coding · LiveCodeBench
87.8Kimi K3.1 Pro: not scored yet
Scientific coding · SciCode
3460.8Terminal tasks · Terminal-Bench 4.0
067.2Tool use · τ-Bench Banking
12.8Kimi K3.1 Pro: not scored yet
Instruction following · IFBench
69Kimi K3.1 Pro: not scored yet
Long documents · AA-LCR
5286.3Competition math · AIME 2025
93.4Kimi K3.1 Pro: not scored yet
Uncensored · UGI
19.7Kimi K3.1 Pro: not scored yet
The specs
| Spec | GPT OSS 120B | Kimi K3.1 Pro |
|---|---|---|
| Input price | $0.10 per 1M | $2 per 1M |
| Output price | $0.50 per 1M | $10 per 1M |
| Cost per test task | $0.1076 | $2.11 |
| Context window | 131K | 1.05M |
| Max output | 131K | 1.05M |
| Accepts | Text | Text, Image, Video |
| Open weights | Yes | Yes |
| Lab | OpenAI | Kimi |
| Released | Aug 2025 | Oct 2026 |
| Knowledge cutoff | Jun 2024 | 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 OSS 120B or Kimi K3.1 Pro cheaper?
GPT OSS 120B is cheaper. It charges $0.10 per 1M input tokens and $0.50 per 1M output tokens, against $2 and $10 for Kimi K3.1 Pro. Blended 3 parts input to 1 part output, that is $0.20 against $4 per 1M tokens.
Are GPT OSS 120B and Kimi K3.1 Pro open source?
Both are open-weights models: OpenAI and Kimi publish the weights, so you can download them and run them on your own hardware, or call them through any host's API. Check each model's license before you ship it.
Which is smarter, GPT OSS 120B or Kimi K3.1 Pro?
Kimi K3.1 Pro scores higher on the Artificial Analysis Intelligence Index, 55.1 against 11.6 for GPT OSS 120B. The biggest differences are on Terminal-Bench 4.0 (0 vs 67.2) and AA-LCR (52 vs 86.3).
Which has the longer context window?
Kimi K3.1 Pro accepts 1.05M tokens, against 131K for GPT OSS 120B.
Can I compare GPT OSS 120B and Kimi K3.1 Pro 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 the Epoch Capabilities Index, SimpleQA, OTIS Mock AIME and FrontierMath, which are from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard, and CursorBench, which is from Cursor, and FrontierCode, which is from Cognition at each model’s best-scoring effort. 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 November 18, 2026.