AfterQuery

We're thrilled to announce our $30M Series A at a $300M valuation led by @altosvc, and that we’ve since surpassed $100M in annual revenue run rate.

@AfterQuery will be at ICLR next week! We’ll be at booth 404. Happy to chat about anything related to tool use/agents, RL environments, code gen, or evals.  DM me if you wanna meet up!

AfterQuery post-trained GPT-OSS-20B using Harbor + Tinker and saw a 14% bump on TB2 performance. Love seeing people pick up Harbor for more than just evals.

Paper: arxiv.org/abs/2601.20886

Introducing IDE-Bench! A multi-language, full-stack benchmark evaluating LLMs acting as autonomous IDE agents IDE-Bench assesses agents' ability to navigate, reason, and modify complex repositories using the same tools available in modern AI-native IDEs like Cursor Models tested from @AnthropicAI, @OpenAI, @Alibaba_Qwen, @GoogleDeepMind, @xai, @deepseek_ai, @Meta, and @cohere Check out the full results at ide-bench.com!

RT @spencermateega: Congrats to @ValsAI team for launching Finance Agent Benchmark v1.1! Proud that @AfterQuery could contribute finance e…

Our findings show that current models lack the ability to perform even the most basic tasks in high-impact, real-world domains like quantitative trading. We hope Market-Bench can serve as a shared framework to evaluate models’ understanding of trading strategies and code generation for quantitative finance. Excited to track how these capabilities evolve!

Leaderboard: marketbench.ai Paper: arxiv.org/abs/2512.12264

Introducing Market-Bench by @AfterQuery! The first-of-its-kind benchmark on LLMs for quantitative finance. We challenged models to attempt a frequent introductory quantitative trading task: coding an executable backtester from a natural-language strategy description and market assumptions. > 13 models build backtesting systems for directional, pair trading, and delta hedging strategies > evaluated on reliability (executable passes) and accuracy (MAE) across 5 attempts per strategy > real order book data with exchange delays and liquidity constraints > @xAI’s Grok 4 achieved the overall lowest mean MAE (deviation from the golden backtest), followed closely by @OpenAI’s GPT 5.2 > @AnthropicAI's Sonnet 4.5 and @AlibabaGroup's Qwen 3 Max at perfect executability but high MAE > Models from @Meta, @Amazon, @NVIDIA, and @Cohere continued to fail to produce executable backtesters Leaderboard & full paper below!

How far can vibe coding actually go? Introducing App-Bench by @AfterQuery, a benchmark for end-to-end web app development. We tested 6 production web apps on 10 coding agents from @OpenAI, @GoogleDeepMind, @AnthropicAI, @cursor_ai, @budapp, @v0, @boltdotnew, @Replit, and @Lovable. One shot generation. Zero human edits. 4,530 evaluations.

@cigdemoztabak_ 👀

what a grand opening! watching @AfterQuery

Really excited to have contributed to this sick creative vision and brought the @AfterQuery website to life 😎😎

Today, humanity is shackled by scarcity of expertise. When expertise becomes infinitely scalable, humans will be freed to tackle problems we can't even conceive of today. Introducing @AfterQuery. We’re building a world where expertise is abundant. Domain by domain, profession by profession, AfterQuery is crafting datasets that encode excellence into forms that machines can learn. Data is the final frontier.

@shrawberryy @sashabirukoff shrawberry 🙌

website and brand identity i did for @AfterQuery !! site design, visuals, copy, animations all by me - logo in collaboration with @sashabirukoff more details soon yippeeee

The frontier begets the frontier. I highly recommend reading @jaminball's latest Clouded Judgement article which spells out the AfterQuery thesis (thread)

Excited for UI-Bench to be the leading benchmark for UI/web design! Congrats to the @figma make team for claiming the #2 ranking

Introducing UI-Bench by @afterquery. The first and only rigorous eval of vibe coding tools. > 4,000+ blinded pairwise judgments > @budapp, @figma make, and @lovable take the lead > @v0 and @replit ranked dead last > performance gaps = differences in LLM orchestration, prompting, design templates, and post-processing > link to our paper in the comments!