Apodex ✓
@Apodex_AI
The World's First Self-Evolving Heavy-Duty Solver Try: https://t.co/AxyXwFyUUD • https://t.co/vKq0rcX7R3 • https://t.co/fSgXwKhshx
5 416Followers
210Following
218Posts total
3MViews on collected posts
Latest posts
Looking for new posts…
@Apodex_AI The persistent state and mid-task intervention are what really I really love here. Scaling intelligence is not just about a bigger model, it’s about building agents that can actually manage complex work from start to finish.
11.3K views · 22 likes
· 0 reposts · 15 replies
Open on X →
@Apodex_AI This is the gap that actually matters.
AI agents can produce impressive outputs, but scientific workflows demand more than running tools and claiming success. Results must be complete, reproducible, and verifiable.
FrontierChallenge exposes how far we still are from
3.2K views · 17 likes
· 0 reposts · 23 replies
Open on X →
We’re also introducing FrontierSearchBench — 41 verifiable deep-search tasks designed to test whether deep research agents are actually correct, not just plausible.
Each task is scored against structured ground truth by its own program.
Wrong claims are penalized.
A detailed,
1.7K views · 27 likes
· 2 reposts · 4 replies
Open on X →
Everyone says AI agents can already analyze data, run code, generate figures, and write reports.
But can they actually complete a scientific workflow?
Explore FrontierChallenge — now #2 on today’s Hugging Face Daily Papers: https://t.co/U0jAZd8l8s
Today, we’re introducing htt
256.5K views · 251 likes
· 154 reposts · 214 replies
Open on X →
1:25
Apodex 1.1 mini — 35B, open weights, and built for local deployment.
With Agent Team: 50.2 FrontierFinance · 51.7 FrontierScience-Research · 27.7 APEX-Agents—virtually matching the 1T-parameter Kimi K2.6 at 27.9. With ReAct: 40.0 · 45.0 · 24.2.
FrontierAgent is open-sourced http
24.3K views · 166 likes
· 80 reposts · 127 replies
Open on X →
Two scaling surfaces, one shared execution foundation.
1. Environment Scaling — expanding the file, search, code, and other executable environments the model can learn and act in.
2. Agentic Coordination Scaling — expanding a task’s ability to be broken down, coordinated, https:/
48.9K views · 130 likes
· 69 reposts · 114 replies
Open on X →
Where Apodex 1.1 lands.
▸ Professional work — APEX-Agent 38.5 · GDPVal 78.8 win rate
▸ Finance — FrontierFinance 54.3
▸ Scientific research — FrontierScience-Research 63.3 · BioMysteryBench Human-difficult 35.3
▸ Reasoning — HLE 56.1
📊 Across the four benchmarks evaluated https
33.7K views · 194 likes
· 72 reposts · 124 replies
Open on X →
Meet Apodex 1.1: Scaling Agentic Intelligence for Complex Work
Open Source Harness: https://t.co/hXoOuuWhlk
Open Weights: https://t.co/tudzx5etWt
We’re excited to introduce Apodex 1.1, our new model family built to scale agentic intelligence for professional work.
🧠 https://t.
910.9K views · 1.9K likes
· 456 reposts · 358 replies
Open on X →
@Apodex_AI Haha Big boss making the switch into the AI industry to innovate again is a probability worth learning from. Having AI hypothesize possible futures and then go verify the results is genuinely a forward-thinking idea — looking forward to seeing it come to fruition.
1.1K views · 14 likes
· 0 reposts · 18 replies
Open on X →
Today, in full: the technical report — the definitions, the rubric, the registry of problems — spanning biomedicine, clinical translation and frontier-model engineering. Led by Apodex’s Lead Scientist @profshengwang, who brings together the technical framework behind this effort.
3K views · 98 likes
· 9 reposts · 4 replies
Open on X →
So what does TRACES actually measure? Not just the answer, but the path to the answer.
Six capabilities that spell its name:
*T — Tools: selecting, calling and correctly interpreting external tools
*R — Repair: locating and correcting its own errors once feedback arrives
*A —
6.4K views · 117 likes
· 14 reposts · 4 replies
Open on X →
Most AI benchmarks test retrieval — can a model find the known answer? However, the hardest problems in science require discovery, can a system earn an answer nobody has yet?
Meet TRACES 🧭 — the world's first benchmark for measuring discoverative AI: AI that can work through htt
1.7M views · 1.1K likes
· 708 reposts · 524 replies
Open on X →
Against accounts of the same size
12 posts from the last 90 days, next to the under 10K follower range. shown to more people than peers of the same size.
Median views17 770this account4 175median for under 10K
Reach, %328.11%this account250.82%median for under 10K
Engagement, %1.26%this account1.41%median for under 10K
| Metric | This account | Median for under 10K | Ratio |
|---|---|---|---|
| Median views per post | 17 770 | 4 175 | 4.26× |
| Reach (views ÷ followers) | 3.3× audience | 2.5× audience | 1.31× |
| Engagement rate | 1.26% | 1.41% | 0.89× |
Others in this range → Compare with another account → How these benchmarks are built →
Growth & engagement
How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.
Views per post
1.7M19 Aug
6.4K
3K
1.1K20 Aug
910.9K24 Aug
33.7K
48.9K
24.3K
256.5K27 Aug
1.7K
3.2K29 Aug
11.3K30 Aug
Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.
Engagement rate per post
0.16%19 Aug
2.15%
3.66%
3.05%20 Aug
0.33%24 Aug
1.28%
0.73%
1.72%
0.29%27 Aug
1.94%
1.23%29 Aug
0.33%30 Aug
Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.41%.
What the audience does
Likes37.3%4 002 in total
Reposts14.6%1 564 in total
Replies14.2%1 529 in total
Quotes8.8%950 in total
Bookmarks25.1%2 695 in total
Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.
The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.
Similar accounts
Grace Clarke ✓
@graceclarke
10.8K followers
· 23.2K posts
Amit Shah
@theamitshah
10.8K followers
· 5.9K posts
Shilen Patel ✓
@shilensays
10.8K followers
· 572 posts
Dominique♍️
@DomaLatrice
10.8K followers
· 172.5K posts
Türk'ün Zaferi ✓
@T_zaferi9
10.8K followers
· 10.6K posts
Daryl Daleen
@CoachDaleen
10.8K followers
· 540 posts
tati • ana 🛸 ✓
@91rare
10.8K followers
· 154.8K posts
Daddan Mishra ( Modi ka parivar )
@daddanmishra
10.8K followers
· 38.4K posts