Vals AI ✓

@ValsAI · San Francisco, CA · joined 07 Mar 2024

Public LLM Evaluation // https://t.co/rNS39rhVQ9 @8vc @BloombergBeta @pearvc @a16z @HRTVentures @nextladder

17 651Followers

272Following

1 808Posts total

214.9KViews on collected posts

Against accounts of the same size

5 posts from the last 90 days, next to the 10K–100K follower range. shown far beyond its own audience, and the audience reacts.

Median views6 504this account2 578median for 10K–100K

Reach, %36.85%this account7.77%median for 10K–100K

Engagement, %1.93%this account1.47%median for 10K–100K

Metric	This account	Median for 10K–100K	Ratio
Median views per post	6 504	2 578	2.52×
Reach (views ÷ followers)	36.85%	7.77%	4.74×
Engagement rate	1.93%	1.47%	1.31×

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

185.8K1 Sep

3.2K3 Sep

6.5K

17.5K4 Sep

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.93%1 Sep

1.93%3 Sep

0.71%

2.32%

2.41%4 Sep

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.47%.

What the audience does

Likes71.3%2 072 in total

Reposts5.6%164 in total

Replies2.5%74 in total

Quotes2.1%60 in total

Bookmarks18.4%536 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.

Latest posts

GPT 6 Astra has smashed the record on our Code Migration benchmark, #1 at 68% accuracy (+10 points over second place). It's also 2-4x faster than the comparable models. https://t.co/8nIMNiYpRs 17.5K views · 366 likes · 27 reposts · 23 replies 04 Sep 2026 OpenAI’s GPT 6 Astra has effectively saturated SRE-Bench, a cybersecurity benchmark testing whether models can reverse engineer binaries. We’re sharing more information, along with a call for contributions to extend the benchmark: https://t.co/K13uyPgPOM 6.5K views · 141 likes · 5 reposts · 3 replies 03 Sep 2026 Gov. Shapiro just signed an execute order establishing stringent AI data center regulations, focusing on energy, water and community burdens. But measurements of the environmental footprint of AI are incomplete outside the context of how the technology is used. Our new https://t. 2K views · 10 likes · 2 reposts · 1 replies 03 Sep 2026 GLM 5.3 Flash (codenamed ox-alpha) is #8 among open-weight models on the Vals Index - 6 spots behind GLM 5.3, but costs roughly 18x less than GLM 5.3. https://t.co/PrjtH1kb1q 3.2K views · 56 likes · 1 reposts · 4 replies 03 Sep 2026 Using Fable 5.1, we’ve elicited a decoding of a cipher that has been unsolved for 373 year, and listed as #28 on Klaus Schmeh’s (the most-published cryptology author in the world) “The Top 50 unsolved encrypted messages.” The solution? Almost embarrassingly simple in hindsight. 185.8K views · 1.5K likes · 129 reposts · 43 replies 01 Sep 2026