RL environments and AI benchmarks, cataloged daily.

Vals AI @ValsAI

We tested 18 AI chatbots on teen safety with SAFE-Teen, the first teen safety benchmark built with clinicians that follows whole conversations instead of grading the first answer. Every chatbot failed. 54.0% of conversations had at least one safety failure. The range was wide: 14.0% for GPT-6.1 Sol, 62.4% for Gemini 3.8 Flash.

— Vals AI (@ValsAI) Oct 20, 2026

Collinear @collinearAI

We just got back from #COLM2026 with four papers we loved on collaboration, human simulation, personalized rewards, and longer-horizon RL. Here’s the first. 🧵 (1/4) An agent’s autonomous ranking may not predict how well it works with people. CollabSkill, by @EchoShao8899, @Diyi_Yang et al., explores that gap. 🤝 93 professionals worked with 5 agents across 386 sessions on occupational tasks. A Bayesian skill rating estimates the separate contributions of humans and agents. 🔄 Among the terminal agents tested, Claude Code outranks Codex in collaboration, reversing their order on the autonomous benchmarks compared in the paper. Claude Cowork ranks first overall, using the same Claude Sonnet 4.6 model as Claude Code through a different interface. These results apply to the versions tested. 👥 Teams with top-quartile collaborators beat the same agent running solo 74% of the time; bottom-quartile collaborators win 27%. 📄

— Collinear (@collinearAI) Oct 20, 2026

Modal @modal

Voice agents, multiplayer games, and other workloads need to maintain continuity between requests. With Sticky Sessions, built on Modal's serverless Servers, you can route requests in a session to the same container and autoscale with demand. Here's a look at how we built it:

— Modal (@modal) Oct 20, 2026

Scale AI @scale_ai

From classrooms to legislative drafting, AI is being built into specialized government workflows. Through a multi-year partnership with @MCITQatar, Scale is one of the partners contributing to AI adoption across Qatar’s public institutions. What that looks like in practice ↓

— Scale AI (@scale_ai) Oct 20, 2026

BenchFlow @benchflow_ai

Dream!

— BenchFlow (@benchflow_ai) Oct 20, 2026

Surge AI @HelloSurgeAI

Could AI actually solve the Riemann Hypothesis? That's the question that inspired Riemann-bench. We wanted to go beyond Olympiad math and test whether AI could tackle difficult, research-level problems from top mathematicians. Six months ago, models scored under 5%. Today, they're above 70% (10,000 agents not allowed!), and Navier-Stokes and UGC have now been solved. With all the recent breakthroughs, we have an internal betting pool with two predictions: the Riemann Hypothesis will be solved within a year, and P vs NP will be the last Millennium problem to fall. Great to see Riemann-bench featured in this year's @stateofai Report, and who can even imagine next year's?

— Surge AI (@HelloSurgeAI) Oct 20, 2026

Gray Swan AI @GraySwanAI

Not sure where to start on our current $300K challenge? Get some help during one of our live Discord AMAs: - Tue 10/20, 12:30pm PT - Wed 10/21, 1:30pm PT - Fri 10/23, 1:30pm PT Tune in at

— Gray Swan AI (@GraySwanAI) Oct 20, 2026

Ooak Data @Ooakdata

Most AI agents are trained in fake offices. We build digital twins of real ones. What’s a digital twin? A copy of a real company, with the same tools, workflows and code, where AI agents learn to do real work. Same people, same structure. All identities are anonymized.

— Ooak Data (@Ooakdata) Oct 20, 2026

micro1 @micro1_ai

The most advanced AI models still get nearly half of expert contract review judgments wrong. We partnered with @heyivoai to examine why, and where even the most advanced models fall short when reviewing and negotiating real contracts. Introducing the Ivo-micro1 ContractBench, a benchmark built by practicing attorneys to test how well AI handles the judgment calls that come with reviewing a contract, not just whether it can draft. No model scored above 59%. Models did well on the straightforward calls, like leaving acceptable language alone or applying a clear playbook rule, but they struggled most on the issues attorneys considered highest priority. Knowing what to push back on, what to leave alone, and when to escalate proved challenging for the models evaluated. Explore the full results and methodology below.

— micro1 (@micro1_ai) Oct 20, 2026

Mercor @mercor

Mercury 3, @_inception_ai's diffusion LLM, debuts on the APEX leaderboards. 50.2% Pass@1 on APEX-Agents (#30 of 59) 43.1% Pass@1 on APEX-SWE (#31 of 62) Inception positions Mercury 3 against speed-optimized frontier models. On APEX-Agents it lands between GPT-6 Luna and Haiku 5.5, and on coding it trails Haiku 5.5 by 12 points. Across APEX-Agents domains (mean score): Corporate law: 78.4% Management consulting: 57.5% Investment banking: 51.4% It is cost pareto optimal on APEX-Agents. An average APEX-Agents task costs about 6 cents at Inception's list price, and about 3 cents at the launch discount, helped by heavy prompt caching. Congratulations to the Inception team on showing a diffusion model can hold its own on long-horizon professional work. See full leaderboard:

— Mercor (@mercor) Oct 20, 2026