vanta-research/atom-27b
Text Generation
•
27B
•
Updated
•
42
•
1
Tyler Williams PRO
unmodeled-tyler
AI & ML interests
AI research engineer. The human behind VANTA Research.
[email protected]
Recent Activity
updated
a model
17 minutes ago
vanta-research/atom-27b
reacted
to
mike-ravkine's
post
with 🔥
27 minutes ago
Happy 2026 everyone!
I've been busy working on some new ranking/position methodologies and excited to start sharing some results.
Plot legends:
- X = truncation rate (low = good)
- ? = confusion rate (low = good)
- blue bars = average completion tokens (low = good)
- black diamonds = CI-banded performance (high = good)
- cluster squares = models inside this group are equivalent
https://huggingface.co/openai/gpt-oss-120b remains the king in all dimensions of interest: truncation rates, completion lengths and performance. If I had but one complaint it's the reason_effort does not seem to actually work - more on this soon.
Second is a 3-way tie in performance between the Qwen3-235B-2507 we all know and love with an unexpected entrant - https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct
This is a very capable model and it's reasoning effort controls actually works, but you should absolutely not leave it on the default "unlimited" - enable a sensible limit (4k works well for 8k context length).
Third place is another 3-way tie, this one between Seed-OSS-36B (it straddles the CI boundary between 2nd and 3rd place), https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct (demonstrating that full attention may be overrated after all and gated is the way to go) and the newly released https://huggingface.co/zai-org/GLM-4.7 which offers excellent across the board performance with some of the shortest reasoning traces I've seen so far.
Organizations
updated
a
model
17 minutes ago
reacted to
mike-ravkine's
post with 🔥
27 minutes ago
Post
3
Happy 2026 everyone!
I've been busy working on some new ranking/position methodologies and excited to start sharing some results.
Plot legends:
- X = truncation rate (low = good)
- ? = confusion rate (low = good)
- blue bars = average completion tokens (low = good)
- black diamonds = CI-banded performance (high = good)
- cluster squares = models inside this group are equivalent
openai/gpt-oss-120b remains the king in all dimensions of interest: truncation rates, completion lengths and performance. If I had but one complaint it's the reason_effort does not seem to actually work - more on this soon.
Second is a 3-way tie in performance between the Qwen3-235B-2507 we all know and love with an unexpected entrant - ByteDance-Seed/Seed-OSS-36B-Instruct
This is a very capable model and it's reasoning effort controls actually works, but you should absolutely not leave it on the default "unlimited" - enable a sensible limit (4k works well for 8k context length).
Third place is another 3-way tie, this one between Seed-OSS-36B (it straddles the CI boundary between 2nd and 3rd place), Qwen/Qwen3-Next-80B-A3B-Instruct (demonstrating that full attention may be overrated after all and gated is the way to go) and the newly released zai-org/GLM-4.7 which offers excellent across the board performance with some of the shortest reasoning traces I've seen so far.
I've been busy working on some new ranking/position methodologies and excited to start sharing some results.
Plot legends:
- X = truncation rate (low = good)
- ? = confusion rate (low = good)
- blue bars = average completion tokens (low = good)
- black diamonds = CI-banded performance (high = good)
- cluster squares = models inside this group are equivalent
openai/gpt-oss-120b remains the king in all dimensions of interest: truncation rates, completion lengths and performance. If I had but one complaint it's the reason_effort does not seem to actually work - more on this soon.
Second is a 3-way tie in performance between the Qwen3-235B-2507 we all know and love with an unexpected entrant - ByteDance-Seed/Seed-OSS-36B-Instruct
This is a very capable model and it's reasoning effort controls actually works, but you should absolutely not leave it on the default "unlimited" - enable a sensible limit (4k works well for 8k context length).
Third place is another 3-way tie, this one between Seed-OSS-36B (it straddles the CI boundary between 2nd and 3rd place), Qwen/Qwen3-Next-80B-A3B-Instruct (demonstrating that full attention may be overrated after all and gated is the way to go) and the newly released zai-org/GLM-4.7 which offers excellent across the board performance with some of the shortest reasoning traces I've seen so far.
reacted to
dhruv3006's
post with ❤️
about 19 hours ago
Post
2402
Git is powerful, but it’s also one of the biggest sources of developer mistakes.
What is Git GUI, and how does it help here ?
Git GUI makes version control visual, predictable, and easier to reason about especially when things go wrong.
That’s exactly why we built Git GUI in Voiden.
Instead of relying on memorized commands, Voiden lets you see what Git is doing before it does it.
What Voiden’s Git GUI helps developers do
• View exact file and line-level changes before committing
• Stage only intended changes (no accidental commits)
• Clearly distinguish staged vs unstaged files
• Inspect visual diffs with full context
• Understand branches, commit history, and repo state instantly
When Git behavior is hidden, errors increase. Voiden’s Git GUI doesn’t abstract Git away, it explains Git.
Whether you’re new to Git or an experienced developer who prefers clarity, this is Git you can reason about.
Version control should feel safe, not stressful.
What Git pain points slow you down today?
Try out Git GUI in beta : https://voiden.md ( Now in Linux and Mac )
What is Git GUI, and how does it help here ?
Git GUI makes version control visual, predictable, and easier to reason about especially when things go wrong.
That’s exactly why we built Git GUI in Voiden.
Instead of relying on memorized commands, Voiden lets you see what Git is doing before it does it.
What Voiden’s Git GUI helps developers do
• View exact file and line-level changes before committing
• Stage only intended changes (no accidental commits)
• Clearly distinguish staged vs unstaged files
• Inspect visual diffs with full context
• Understand branches, commit history, and repo state instantly
When Git behavior is hidden, errors increase. Voiden’s Git GUI doesn’t abstract Git away, it explains Git.
Whether you’re new to Git or an experienced developer who prefers clarity, this is Git you can reason about.
Version control should feel safe, not stressful.
What Git pain points slow you down today?
Try out Git GUI in beta : https://voiden.md ( Now in Linux and Mac )
- 2 replies
reacted to
MohamedRashad's
post with ❤️
about 19 hours ago
Post
3155
I have update my https://huggingface.co/collections/MohamedRashad/arabic-speech-datasets
with new datasets, making the full audio data more than 3000 hours of good arabic speech.
Feel Free to use it in your new innovations, And happy new year!
with new datasets, making the full audio data more than 3000 hours of good arabic speech.
Feel Free to use it in your new innovations, And happy new year!
updated
a
collection
about 21 hours ago
updated
11
models
about 21 hours ago
vanta-research/atom-olmo3-7b
Text Generation
•
7B
•
Updated
•
37
•
5
vanta-research/atom-v1-preview-12b
Text Generation
•
12B
•
Updated
•
263
•
5
vanta-research/atom-v1-preview-4b
Text Generation
•
4B
•
Updated
•
1.07k
•
7
vanta-research/scout-8b
8B
•
Updated
•
5
vanta-research/scout-4b
Text Generation
•
4B
•
Updated
•
1.78k
•
11
vanta-research/wraith-8b
Text Generation
•
8B
•
Updated
•
246
•
6
vanta-research/atom-astronomy-7b
Text Generation
•
7B
•
Updated
•
42
•
2
vanta-research/apollo-astralis-2
Text Generation
•
9B
•
Updated
•
2
vanta-research/apollo-astralis-4b
Text Generation
•
4B
•
Updated
•
56
•
6
vanta-research/apollo-v1-7b
Text Generation
•
Updated
•
56
•
2
vanta-research/apollo-astralis-8b
Text Generation
•
8B
•
Updated
•
1.01k
•
11
reacted to
their
post with 🚀
about 22 hours ago
Post
98
NEW MODEL ALERT:
vanta-research/atom-27b
Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+
Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.
Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.
Check it out!
Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+
Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.
Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.
Check it out!
posted
an
update
about 22 hours ago
Post
98
NEW MODEL ALERT:
vanta-research/atom-27b
Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+
Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.
Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.
Check it out!
Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+
Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.
Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.
Check it out!
liked
a
model
about 22 hours ago
published
a
model
about 22 hours ago