Research

Mengqi Yuan (XLANG Lab, University of Hong Kong) presents OSWorld 2.0, a benchmark of 108 long-horizon, real-world computer-use workflows where even frontier AI agents complete only 20.6% of tasks outright after 300+ steps each.

Mengqi Yuan (XLANG Lab, University of Hong Kong) presents OSWorld 2.0, a benchmark of 108 long-horizon, real-world computer-use workflows where even frontier AI agents complete only 20.6% of tasks outright after 300+ steps each.

We evaluated Fable 5.1 on a series of frontier coding tasks from our proprietary Terminal-Bench+ dataset and compared the results against Opus 5. Fable remained competitive across most categories and was materially more efficient on successful runs, while its gap was concentrated in a small set of terminal-heavy and build/dependency tasks. Because category sizes are small and uneven, we treat

The speed of new frontier model releases keeps accelerating. Meanwhile benchmarks struggle to keep up and saturate quickly, often being left in the dust. Most benchmarks are static datasets with no active maintenance, causing them to lose value fast. Some benchmarks are looking to change this by becoming Continuous Benchmarks. Terminal-Bench is one of the most widely reported benchmarks on

Terminal-Bench 3.0 (formerly Frontier-Bench) recently launched, built to track what AI agents can and can’t do across real computer work. Terminal-Bench 2.1 has been saturating, with top agents reaching 84%; on Terminal-Bench 3.0, the best model, Claude Opus 5, achieves just 43.5%. Terminal-Bench 3.0 raises the bar with 74 authentic, verifiable tasks across 7 domains, designed to expose meaningful gaps

Parth Asawa (UC Berkeley) presents Continual Learning Bench, the first expert-validated benchmark built to measure whether LLM-based systems genuinely improve with experience, spanning six real-world domains from software engineering to outbreak forecasting.

Nicholas Roberts presents Train-to-Test (T²) scaling laws, which jointly optimize model size, training tokens, and test-time samples—and show why reasoning models should be overtrained well beyond Chinchilla-optimal ratios.

Long-horizon agents operate across many dependent states and transitions, often spanning multiple tools, environments, and periods of external feedback. The difficulty comes from preserving coherent progress as earlier decisions constrain later actions. A single workflow may involve researching evidence, changing files or records, waiting for external responses, revising plans, validating intermediate results, and returning to earlier systems with new information.

Most agent benchmarks still evaluate a thin slice of the job. The agent receives a task, produces an answer, gets scored, and the episode ends. Enterprise workflows work differently. An underwriting agent may need to read policy documents, inspect customer records, call internal tools, ask a simulated user for missing information, update state, and follow approval rules. A correct final

Anthropic’s Claude Opus 5 recently debuted as the second model overall on the current Senior SWE-bench leaderboard, behind Fable 5. It also achieves the highest score of any evaluated model on the benchmark’s Bug & Performance Investigation category, reinforcing the rapid progress frontier coding models continue to make on increasingly realistic software engineering tasks. Just as notable, Opus 5 reaches

At our latest Snorkel AI Reading Group, Henry Ehrenberg presented Senior SWE-Bench, an open-source, Harbor-compatible benchmark for evaluating coding agents on realistic, senior-level software engineering work. Its 100 tasks, with 50 public and 50 kept private to mitigate contamination, are sourced from real pull requests across 12 production repositories and cover complex features, migrations, bugs, and performance issues. Senior SWE-Bench

We’ve evaluated Grok 4.5 on Snorkel’s GDPval+ dataset, Snorkel’s expert-created dataset of professional workplace reasoning tasks from across the economy. To compare performance against other frontier models, we ran the evaluation alongside GPT 5.5 and Claude Opus 4.8. Overall, Grok 4.5 demonstrated the strongest overall performance. Dataset GDPval+ is part of the Snorkel Data Series (SDS), Snorkel’s portfolio of expert-curated

At our latest Snorkel AI Reading Group, Yiyou Sun and David (Xinyang) Han (UC Berkeley, Center for Responsible and Decentralized Intelligence) presented Agents’ Last Exam (ALE) — a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. ALE is a collaboration between Berkeley RDI, Snorkel AI, and 300+ expert contributors across 55 professional subfields. ALE asks a deceptively simple question: can

Most agent benchmarks evaluate each task as an independent episode. The agent receives a task, produces an answer, gets scored, and moves on. The next task starts as if the previous one never happened. That setup misses a core requirement for deployed agents. A coding agent, research assistant, data analyst, or workplace assistant should improve as it works across repeated

For our third Benchtalks, the series dedicated to the researchers building the measurement toolkits that frontier labs hill-climb on, Snorkel AI co-founder Vincent Sunn Chen sat down with Parth Asawa, a PhD student at UC Berkeley advised by Matei Zaharia and Joey Gonzalez. Parth leads research on continual learning and is the creator of Continual Learning Bench, developed in collaboration