Proximal

@ProximalHQ

Advancing coding intelligence.

4 430Followers

0Following

113Posts total

348.8KViews on collected posts

Ultimi post

Proximal@ProximalHQ2 Sep

@ProximalHQ Pretty cool to see a benchmark actually discriminate between flagship models 2.1K views · 22 likes · 0 reposts · 2 replies Open on X →

Proximal@ProximalHQ2 Sep

Read more about FrontierSWE: Blog: https://t.co/CPTu3JdUEs Github: https://t.co/HxEhnRfDjm 4.4K views · 43 likes · 2 reposts · 2 replies Open on X →

Proximal@ProximalHQ2 Sep

We also observe a large amount of cheating and sandbox escape attempts, and notably, attempts to consciously conceal cheating rather than "cheating by accident" We are still investigating these incidents and will share an more detailed analysis in a follow-up blog post https://t 4.9K views · 62 likes · 2 reposts · 2 replies Open on X →

Proximal@ProximalHQ2 Sep

GLM 5.3, the third-best model on FrontierSWE and strongest open source model, does not have native vision capabilities (we are currently testing GLM-5.3 Flash, which has vision support) In visual tasks, we observe GLM converting images to ASCII art to read their contents https:/ 6.3K views · 63 likes · 3 reposts · 1 replies Open on X →

Proximal@ProximalHQ2 Sep

We see impressive capabilities from frontier models when asked to work on open-ended tasks for a long time. In Astronomy Toolkit, Fable 5.1 creates synthetic images of skies and verifies that its position prediction model is not confident to detect potential miscalibration https 4.8K views · 42 likes · 0 reposts · 1 replies Open on X →

Proximal@ProximalHQ2 Sep

Deepseek V4 Flash, Gemini 3.7 Flash, GLM-5.3 and Claude Fable 5.1 are on the cost pareto frontier for FrontierSWE v2 While GPT-5.6 Sol is not cheaper than Fable 5.1, it does spend significantly less time per task https://t.co/HMgYESK4TR 7K views · 54 likes · 2 reposts · 3 replies Open on X →

Proximal@ProximalHQ2 Sep

FrontierSWE v2 uses proximus, our minimal agent harness which extends mini-swe-agent for ultra-long horizon tasks. When an agent wants to submit a solution, proximus encourages it to work longer. This way, models don't submit prematurely and achieve much better results https://t 8.7K views · 69 likes · 1 reposts · 2 replies Open on X →

Proximal@ProximalHQ2 Sep

A new capability we test for is visual reasoning. In TORCS Racing Bot, agents have to build a bot that plays a racing game - the optimal solution requires training an agent via RL In the video below, you can see a bot built by GPT-5.6 Sol attempt a track and crash https://t.co/9 9.1K views · 80 likes · 3 reposts · 1 replies Open on X →

Proximal@ProximalHQ2 Sep

We have expanded FrontierSWE's research tasks and added new problems in the domain of scientific computing In Astronomy Toolkit, agents have to determine where telescope images point without being given their location by matching stars in each image against the Gaia catalogue ht 11.3K views · 89 likes · 2 reposts · 1 replies Open on X →

Proximal@ProximalHQ2 Sep

We are releasing FrontierSWE v2, our updated ultra-long horizon coding benchmark V2 features an expanded task suite and improved methodology. We see large performance gaps between frontier models, with Claude Fable 5.1 leading by a wide margin https://t.co/VBXoMgMI0e 290.2K views · 1.2K likes · 131 reposts · 91 replies Open on X →

Rispetto ad account della stessa dimensione

10 post degli ultimi 90 giorni, accanto alla fascia di under 10K follower. sotto i pari sia per copertura sia per interazione.

Visualizzazioni mediane6 650questo account4 175mediana per under 10K

Copertura, %150.10%questo account250.82%mediana per under 10K

Interazione, %0.92%questo account1.41%mediana per under 10K

Metrica	Questo account	Mediana per under 10K	Rapporto
Visualizzazioni mediane per post	6 650	4 175	1.59×
Copertura (visualizzazioni ÷ follower)	150.10%	2.5× audience	0.60×
Tasso di interazione	0.92%	1.41%	0.65×

Altri account di questa fascia → Confronta con un altro account → Come sono costruiti questi parametri →

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

290.2K2 Sep

11.3K

9.1K

8.7K

4.8K

6.3K

4.9K

4.4K

2.1K

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.53%2 Sep

0.82%

0.93%

0.85%

0.86%

0.90%

1.08%

1.41%

1.08%

1.15%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.41%.

What the audience does

Likes70.5%1 767 in total

Reposts5.8%146 in total

Replies4.2%106 in total

Quotes3.8%96 in total

Bookmarks15.6%390 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.

Ultimi post

Rispetto ad account della stessa dimensione

Growth & engagement

Views per post

Engagement rate per post

What the audience does

Account simili