mercor.com
mercor.com is A step-by-step account of how we post-trained Qwen3.5-397B: six steps, three of them de-risking, five knobs we ablated, and the full training script.. It is ranked #506 on the Dev Radar, in AI dev tools, first seen 17 days ago and shared in 5 posts (236.3k views).
Training frontier knowledge work agents: A 397B RL training guide with SkyRL | Mercor Blog Research Enterprise Experts Company Sep 1, 2026 Research Training frontier knowledge work agents: A 397B RL training guide with SkyRL Mercor, and SkyRL Mercor, and SkyRL Share A step-by-step account of how we post-trained Qwen3.5-397B-A17B: we focus on the often overlooked infrastructure and derisking work preceding the hero run, show even stronger improvements on a larger model, and release the full training script. This is the third post in our series on post-training open models with Mercor’s expert data. In January, we showed that fewer than 1,000…
What people said about mercor.com on X
How does one RL post-train a 397B model for long-horizon knowledge work? 👩💼 We share every step we took to bring Qwen 3.5 397B from 16.1% Pass@1 to 27.3% on APEX-Agents using DPPO, including final models weights and the full training script🚀 This is the first of many works from Mercor Research on open model…
— @edwardjhu, 17 days ago · 789 likes · see the post
Post-training is becoming more accessible by the day. We're open-sourcing our post-training recipes and the end-to-end process. Every enterprise will soon post-train its own models.
— @BrendanFoody, 17 days ago · 671 likes · see the post
Data is the most important ingredient in post-training. The Mercor Research team focuses on making every hour of expert work yield the most model improvement, through better learning algorithms for knowledge work and automated, domain-specific post-training. We're also committed to doing open source research. That's…
— @mercor, 17 days ago · 98 likes · see the post
Alternatives to mercor.com
- muse.ai — New connectors are live today. Come build with us.
- classifier.dev — now outperforms jev and is free
- mimo-v2.6 RL — Streaming the run
- academy.dair.ai — Chat with Paper
- Union Alpha — Union Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level…
- cua — Draft #3943
mercor.com in numbers
- Rank on the Dev Radar: #506 of 1353
- Shared in 5 posts by 5 accounts: @edwardjhu, @BrendanFoody, @mercor, @sheriyuo
- 236.3k views on those posts
- First seen 17 days ago, last shared 17 days ago
- Pricing seen by Jev: free
- Market: AI dev tools
FAQ
What is mercor.com?
A step-by-step account of how we post-trained Qwen3.5-397B: six steps, three of them de-risking, five knobs we ablated, and the full training script. It was first shared on X 17 days ago and is ranked #506 on the Dev Radar.
Is mercor.com free?
Yes, it is free to use.
Who shared mercor.com?
5 accounts on X, including @edwardjhu, @BrendanFoody, @mercor, in 5 posts totalling 236.3k views.
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.