Daily Papers

Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail. Yet existing agent evaluation mechanisms are limited: benchmarks have low construct validity for application-specific workflows and environments, and replica evaluation environments are expensive and prone to drift. We propose Copy-on-Write (CoW) Scoring, a framework that evaluates agent operations directly within application environments using a PostgreSQL-level Copy-on-Write mechanism to isolate agent writes. CoW Scoring produces session- and operation-level scores that highlight where agents' database write operations succeed and fail in a given application environment, enabling inexpensive evaluation and iteration on agent harnesses and tool surfaces. We demonstrate the framework on Plane, an open-source project-management platform, where analysis surfaced specific issues in the tool surface, and corresponding fixes produced measurable improvements on affected models. Python library: https://github.com/trail-ml/agent-cow-python

Large Language Model (LLM) safety is one of the most pressing challenges for enabling wide-scale deployment. While most studies and global discussions focus on generic harms, such as models assisting users in harming themselves or others, enterprises face a more fundamental concern: whether LLM-based agents are safe for their intended use case. To address this, we introduce operational safety, defined as an LLM's ability to appropriately accept or refuse user queries when tasked with a specific purpose. We further propose OffTopicEval, an evaluation suite and benchmark for measuring operational safety both in general and within specific agentic use cases. Our evaluations on six model families comprising 20 open-weight LLMs reveal that while performance varies across models, all of them remain highly operationally unsafe. Even the strongest models -- Qwen-3 (235B) with 77.77\% and Mistral (24B) with 79.96\% -- fall far short of reliable operational safety, while GPT models plateau in the 62--73\% range, Phi achieves only mid-level scores (48--70\%), and Gemma and Llama-3 collapse to 39.53\% and 23.84\%, respectively. While operational safety is a core model alignment issue, to suppress these failures, we propose prompt-based steering methods: query grounding (Q-ground) and system-prompt grounding (P-ground), which substantially improve OOD refusal. Q-ground provides consistent gains of up to 23\%, while P-ground delivers even larger boosts, raising Llama-3.3 (70B) by 41\% and Qwen-3 (30B) by 27\%. These results highlight both the urgent need for operational safety interventions and the promise of prompt-based steering as a first step toward more reliable LLM-based agents.

While Late Interaction models exhibit strong retrieval performance, many of their underlying dynamics remain understudied, potentially hiding performance bottlenecks. In this work, we focus on two topics in Late Interaction retrieval: a length bias that arises when using multi-vector scoring, and the similarity distribution beyond the best scores pooled by the MaxSim operator. We analyze these behaviors for state-of-the-art models on the NanoBEIR benchmark. Results show that while the theoretical length bias of causal Late Interaction models holds in practice, bi-directional models can also suffer from it in extreme cases. We also note that no significant similarity trend lies beyond the top-1 document token, validating that the MaxSim operator efficiently exploits the token-level similarity scores.

Information Technology (IT) Operations (Ops), particularly Artificial Intelligence for IT Operations (AIOps), is the guarantee for maintaining the orderly and stable operation of existing information systems. According to Gartner's prediction, the use of AI technology for automated IT operations has become a new trend. Large language models (LLMs) that have exhibited remarkable capabilities in NLP-related tasks, are showing great potential in the field of AIOps, such as in aspects of root cause analysis of failures, generation of operations and maintenance scripts, and summarizing of alert information. Nevertheless, the performance of current LLMs in Ops tasks is yet to be determined. In this paper, we present OpsEval, a comprehensive task-oriented Ops benchmark designed for LLMs. For the first time, OpsEval assesses LLMs' proficiency in various crucial scenarios at different ability levels. The benchmark includes 7184 multi-choice questions and 1736 question-answering (QA) formats in English and Chinese. By conducting a comprehensive performance evaluation of the current leading large language models, we show how various LLM techniques can affect the performance of Ops, and discussed findings related to various topics, including model quantification, QA evaluation, and hallucination issues. To ensure the credibility of our evaluation, we invite dozens of domain experts to manually review our questions. At the same time, we have open-sourced 20% of the test QA to assist current researchers in preliminary evaluations of their OpsLLM models. The remaining 80% of the data, which is not disclosed, is used to eliminate the issue of the test set leakage. Additionally, we have constructed an online leaderboard that is updated in real-time and will continue to be updated, ensuring that any newly emerging LLMs will be evaluated promptly. Both our dataset and leaderboard have been made public.

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center dataset. In this work we investigated the generalizability of phase recognition algorithms in a multi-center setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 hours was created. Labels included annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 teams submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n=9 teams), for instrument presence detection between 38.5% and 63.8% (n=8 teams), but for action recognition only between 21.8% and 23.3% (n=5 teams). The average absolute error for skill assessment was 0.78 (n=1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but are not solved yet, as shown by our comparison of algorithms. This novel benchmark can be used for comparable evaluation and validation of future work.

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many reference patches produce close-to-zero runtime changes. Second, we show that public submission rankings depend strongly on the benchmark scoring rule. Among eight public submissions shared by GSO and SWE-fficiency, the official rankings disagree on 9 of 28 pairwise submission comparisons, and SWE-fficiency's leaderboard scoring rule assigns the worst ten tasks overly high score weights of 58.5%-82.8%. Third, looking across 10 public submissions for each task, we find that at least one submission matches or beats the reference patch on 85.3% (384/450) of replay-valid GSO and SWE-fficiency tasks, and beats the unoptimized base code on 99.8% (449/450). Our study complements leaderboard scores by identifying tasks with more reliable performance signals, quantifying per-task score contributions, and exposing the remaining performance gaps that are hidden by aggregate rankings.

Intra-operative recognition of surgical phases holds significant potential for enhancing real-time contextual awareness in the operating room. However, we argue that online recognition, while beneficial, primarily lends itself to post-operative video analysis due to its limited direct impact on the actual surgical decisions and actions during ongoing procedures. In contrast, we contend that the prediction and anticipation of surgical phases are inherently more valuable for intra-operative assistance, as they can meaningfully influence a surgeon's immediate and long-term planning by providing foresight into future steps. To address this gap, we propose a dual approach that simultaneously recognises the current surgical phase and predicts upcoming ones, thus offering comprehensive intra-operative assistance and guidance on the expected remaining workflow. Our novel method, Surgical Phase Recognition and Anticipation (SuPRA), leverages past and current information for accurate intra-operative phase recognition while using future segments for phase prediction. This unified approach challenges conventional frameworks that treat these objectives separately. We have validated SuPRA on two reputed datasets, Cholec80 and AutoLaparo21, where it demonstrated state-of-the-art performance with recognition accuracies of 91.8% and 79.3%, respectively. Additionally, we introduce and evaluate our model using new segment-level evaluation metrics, namely Edit and F1 Overlap scores, for a more temporal assessment of segment classification. In conclusion, SuPRA presents a new multi-task approach that paves the way for improved intra-operative assistance through surgical phase recognition and prediction of future events.

Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may not show whether the requested task was delivered. We study both problems. In a controlled code-as-spec setup, two production Copilot CLI agents (claude-opus-4.7, gpt-5.5) re-implement a React Fluent-UI data table in Angular as a reusable library under a hidden 222-test Playwright oracle across 18 runs and three oracle-availability conditions. Alongside the score, we run a mechanical library audit and check each verdict with a no-op ablation. Without the oracle, the library is present but unfinished, revealed by scores. With the oracle in the loop, the score reaches near-perfect, but from a demo holding the tested behavior directly, the library left dead or absent. We call this building to the test; the broader disposition behind both we call validation self-awareness. The agent does not, on its own, validate what it ships as a user would. Prevalence remains an open question across other agents, signals, and model families. Beyond benchmark scores, dispositions like validation self-awareness merit research attention.

Competition retrospectives are useful when they explain what a leaderboard measured, how hidden evaluation changed conclusions, and which design patterns were rewarded. We revisit the CODS 2025 challenge, a privacy-aware Codabench competition on industrial multi-agent orchestration built on . We combine final rank sheets, a 300-submission server log, 149-team registrations, best-submission exports, the organizer winners report, the companion system paper, and verified planning-track source trees. Five results stand out. First, the public planning leaderboard saturates at 72.73\%, and richer prompts do not improve that peak. Second, hidden evaluation changes the story: public and private scores correlate moderately in planning (r{=}0.69) but negatively in execution (r{=}{-}0.13), with several 45.45\% public execution systems reaching 63.64\% on the hidden set. Third, the term is numerically almost inert in the official composite -- combined on a 0--1 scale with 0--100 percentage scores, it contributes at most 0.05 points per track, and rescaling would swap the top two teams. Fourth, the competition is operationally account-based but substantively team-based: 149 registered teams reduce to 24 with non-zero public scores and 11 fully ranked, while 52.3\% of deduplicated registrations list multiple usernames. Fifth, successful execution methods mostly improve guardrails -- response selection, contamination cleanup, fallback, and context control -- rather than novel agent architectures. These findings identify which behaviors the evaluation rewarded, and motivate scale-aware composites, skill-level diagnostics, and versioned artifact release.

We introduce PentestJudge, a system for evaluating the operations of penetration testing agents. PentestJudge is a large language model (LLM)-as-judge with access to tools that allow it to consume arbitrary trajectories of agent states and tool call history to determine whether a security agent's actions meet certain operating criteria that would be impractical to evaluate programmatically. We develop rubrics that use a tree structure to hierarchically collapse the penetration testing task for a particular environment into smaller, simpler, and more manageable sub-tasks and criteria until each leaf node represents simple yes-or-no criteria for PentestJudge to evaluate. Task nodes are broken down into different categories related to operational objectives, operational security, and tradecraft. LLM-as-judge scores are compared to human domain experts as a ground-truth reference, allowing us to compare their relative performance with standard binary classification metrics, such as F1 scores. We evaluate several frontier and open-source models acting as judge agents, with the best model reaching an F1 score of 0.83. We find models that are better at tool-use perform more closely to human experts. By stratifying the F1 scores by requirement type, we find even models with similar overall scores struggle with different types of questions, suggesting certain models may be better judges of particular operating criteria. We find that weaker and cheaper models can judge the trajectories of pentests performed by stronger and more expensive models, suggesting verification may be easier than generation for the penetration testing task. We share this methodology to facilitate future research in understanding the ability of judges to holistically and scalably evaluate the process quality of AI-based information security agents so that they may be confidently used in sensitive production environments.

We introduce the first version of KWBench (Knowledge Work Bench), a benchmark for unprompted problem recognition in large language models: can an LLM identify a professional scenario before attempting to solve it. Existing frontier benchmarks have saturated, and most knowledge-work evaluations to date reduce to extraction or task completion against a specification. KWBench targets the step before that: recognizing the governing structure of the situation from raw inputs alone. The benchmark contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design. Each task encodes a formal game-theoretic pattern (principal-agent conflict, signaling, mechanism design failure, strategic omission, coalitional dynamics, strategic interdependence) and carries structured ground truth recording the expert reading of the situation and the anticipated failure modes. Models receive raw data and a task prompt with no indication of problem type. Scoring is a three-tier rubric gated by a mandatory conjunctive check. Mandatory criteria encode the predicted wrong paths. We evaluate 16 models. The best model passes on 27.9% of tasks. The top two models agree on only 31.7% of their passes. Among the top 8, 44 tasks are solved by exactly one model; routing across the top 8 covers 50.7% of the benchmark, nearly double the best single model. Conditional on passing, quality scores converge (approx 83% across models); unconditional scores do not. Same models articulate the relevant game-theoretic concept correctly when asked, then fail to apply it unprompted. We release KWBench to shift how frontier models are evaluated on knowledge work, scoring them on whether they recognize the right problem from the situation alone, not only on how well they execute once the problem has been framed for them.

The evaluation of Large Language Models (LLMs) in healthcare has been dominated by physician-centric, English-language benchmarks, creating a dangerous illusion of competence that ignores the interprofessional nature of patient care. To provide a more holistic and realistic assessment, we introduce HealthQA-BR, the first large-scale, system-wide benchmark for Portuguese-speaking healthcare. Comprising 5,632 questions from Brazil's national licensing and residency exams, it uniquely assesses knowledge not only in medicine and its specialties but also in nursing, dentistry, psychology, social work, and other allied health professions. We conducted a rigorous zero-shot evaluation of over 20 leading LLMs. Our results reveal that while state-of-the-art models like GPT 4.1 achieve high overall accuracy (86.6%), this top-line score masks alarming, previously unmeasured deficiencies. A granular analysis shows performance plummets from near-perfect in specialties like Ophthalmology (98.7%) to barely passing in Neurosurgery (60.0%) and, most notably, Social Work (68.4%). This "spiky" knowledge profile is a systemic issue observed across all models, demonstrating that high-level scores are insufficient for safety validation. By publicly releasing HealthQA-BR and our evaluation suite, we provide a crucial tool to move beyond single-score evaluations and toward a more honest, granular audit of AI readiness for the entire healthcare team.

Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering. However, existing medical agent benchmarks primarily evaluate final outputs, providing limited visibility into agent behavior within the research process. To address this gap, we present AutoMedBench, a workflow-aware benchmark for autonomous medical-AI research across diverse medical imaging and multimodal inference tasks, organizing agent execution into a unified five-stage workflow (S1-S5): Plan, Setup, Validate, Inference, and Submit. It comprises long-horizon tasks with each run averaging 33 agent turns, spanning five research tracks: segmentation, image enhancement, visual question answering (VQA), report generation, and lesion detection. Each task is evaluated under two difficulty tiers, Lite and Standard, which use the same data and metrics but differ in the amount of task-brief scaffolding, and each run is scored using both final task performance and S1-S5 stage scores, enabling stage-level analysis from the initial task brief to the final submitted artifact. Across thousands of recorded runs, stage-level scoring reveals that Validate is the weakest workflow stage on average, whereas Setup is the strongest, suggesting that current agents are better at making pipelines executable than at verifying their reliability. Post-run error analysis further shows that verification and submission failures dominate tagged errors, accounting for 37.7% and 38.1% of fired codes respectively, whereas task-understanding errors are rare at 0.9%, and runs with one fired error code have a 48% lower overall score than runs with no error code on average.

Reliable end-to-end clinical report generation has been a longstanding goal of medical ML research. The end goal for this process is to alleviate radiologists' workloads and provide second opinions to clinicians or patients. Thus, a necessary prerequisite for report generation models is a strong general performance and some type of innate grounding capability, to convince clinicians or patients of the veracity of the generated reports. In this paper, we present ASaRG (Automatic Segmentation-assisted Report Generation), an extension of the popular LLaVA architecture that aims to tackle both of these problems. ASaRG proposes to fuse intermediate features and fine-grained segmentation maps created by specialist radiological models into LLaVA's multi-modal projection layer via simple concatenation. With a small number of added parameters, our approach achieves a +0.89\% performance gain (p=0.012) in CE F1 score compared to the LLaVA baseline when using only intermediate features, and +2.77\% performance gain (p<0.001) when adding a combination of intermediate features and fine-grained segmentation maps. Compared with COMG and ORID, two other report generation methods that utilize segmentations, the performance gain amounts to 6.98\% and 6.28\% in F1 score, respectively. ASaRG is not mutually exclusive with other changes made to the LLaVA architecture, potentially allowing our method to be combined with other advances in the field. Finally, the use of an arbitrary number of segmentations as part of the input demonstrably allows tracing elements of the report to the corresponding segmentation maps and verifying the groundedness of assessments. Our code will be made publicly available at a later date.

Many deployments must compare candidate language models for safety before a labeled benchmark exists for the relevant language, sector, or regulatory regime. We formalize this setting as benchmarkless comparative safety scoring and specify the contract under which a scenario-based audit can be interpreted as deployment evidence. Scores are valid only under a fixed scenario pack, rubric, auditor, judge, sampling configuration, and rerun budget. Because no labels are available, we replace ground-truth agreement with an instrumental-validity chain: responsiveness to a controlled safe-versus-abliterated contrast, dominance of target-driven variance over auditor and judge artifacts, and stability across reruns. We instantiate the chain in SimpleAudit, a local-first scoring instrument, and validate it on a Norwegian safety pack. Safe and abliterated targets separate with AUROC values between 0.89 and 1.00, target identity is the dominant variance component (η^2 approx 0.52), and severity profiles stabilize by ten reruns. Applying the same chain to Petri shows that it admits both tools. The substantial differences arise upstream of the chain, in claim-contract enforcement and deployment fit. A Norwegian public-sector procurement case comparing Borealis and Gemma 3 demonstrates the resulting evidence in practice: the safer model depends on scenario category and risk measure. Consequently, scores, matched deltas, critical rates, uncertainty, and the auditor and judge used must be reported together rather than collapsed into a single ranking.

Extent of resection after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. To achieve this, accurate segmentation and classification of residual tumor from post-operative MR images is essential. The current standard method for estimating it is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of extent of resection. In this study, two state-of-the-art neural network architectures for pre-operative segmentation were trained for the task. The models were extensively validated on a multicenter dataset with nearly 1000 patients, from 12 hospitals in Europe and the United States. The best performance achieved was a 61\% Dice score, and the best classification performance was about 80\% balanced accuracy, with a demonstrated ability to generalize across hospitals. In addition, the segmentation performance of the best models was on par with human expert raters. The predicted segmentations can be used to accurately classify the patients into those with residual tumor, and those with gross total resection.

The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications predict selective prediction performance. Twenty frontier LLMs from seven families were evaluated on 524 items across six cognitive tracks. Valid models show mean Type 2 AUROC = .624 (SD = .048). Invalid models show mean AUROC = .357 (SD = .231). Cohen's d = 2.81, p = .002. The tiers order monotonically: Invalid (.357) < Indeterminate (.554) < Valid (.624). Split-half cross-validation yields median d = 1.77, P(d > 0) = 1.0 across 1,000 splits. The three-tier classification accounts for 47% of the variance in AUROC. DeepSeek-R1 drops from 85.3% accuracy at full coverage to 11.3% at 10% coverage. The screen predicts the criterion. For selective prediction, the screen matters.

Information tasks such as writing surveys or analytical reports require complex search and reasoning, and have recently been grouped under the umbrella of deep research -- a term also adopted by recent models targeting these capabilities. Despite growing interest, the scope of the deep research task remains underdefined and its distinction from other reasoning-intensive problems is poorly understood. In this paper, we propose a formal characterization of the deep research (DR) task and introduce a benchmark to evaluate the performance of DR systems. We argue that the core defining feature of deep research is not the production of lengthy report-style outputs, but rather the high fan-out over concepts required during the search process, i.e., broad and reasoning-intensive exploration. To enable objective evaluation, we define DR using an intermediate output representation that encodes key claims uncovered during search-separating the reasoning challenge from surface-level report generation. Based on this formulation, we propose a diverse, challenging benchmark LiveDRBench with 100 challenging tasks over scientific topics (e.g., datasets, materials discovery, prior art search) and public interest events (e.g., flight incidents, movie awards). Across state-of-the-art DR systems, F1 score ranges between 0.02 and 0.72 for any sub-category. OpenAI's model performs the best with an overall F1 score of 0.55. Analysis of reasoning traces reveals the distribution over the number of referenced sources, branching, and backtracking events executed by current DR systems, motivating future directions for improving their search mechanisms and grounding capabilities. The benchmark is available at https://github.com/microsoft/LiveDRBench.

Group Relative Policy Optimization (GRPO) is one of the most widely adopted RLVR algorithms for post-training large language models on reasoning tasks. We first show that GRPO admits an equivalent discriminative reformulation, in which policy optimization maximizes the expected score gap between verified positive and negative rollouts. This reformulation reveals two objective-level limitations: likelihood-misaligned surrogate scores, in which clipped ratio-based scores are optimized rather than the sequence likelihoods that govern generation, and score-insensitive credit assignment, in which rollout-level credit does not reflect the current score gaps between positive and negative rollouts. To address these limitations, we propose ConSPO, a Contrastive Sequence-level Policy Optimization method that uses length-normalized sequence log-probabilities as rollout scores and contrasts verified positive rollouts against negative distractors within the same group. ConSPO optimizes a group-wise InfoNCE-style objective to adaptively strengthen updates for poorly separated positives and high-scoring negatives, together with a curriculum-scheduled margin that preserves separation pressure as training progresses. Experiments across diverse settings show that ConSPO outperforms strong baselines on challenging reasoning benchmarks. Code will be released upon paper acceptance.

Background: AI-based classification models are essential for improving lung cancer diagnosis. However, the relative performance of lesion-level versus chest-region models in internal and external datasets remains unclear. Purpose: This study evaluates the performance of lesion-level and chest-region models for lung cancer classification, comparing their effectiveness across internal Duke Lung Nodule Dataset 2024 (DLND24) and external (LUNA16, NLST) datasets, with a focus on subgroup analyses by demographics, histology, and imaging characteristics. Materials and Methods: Two AI models were trained: one using lesion-centric patches (64,64,64) and the other using chest-region patches (512,512,8). Internal validation was conducted on DLND24, while external validation utilized LUNA16 and NLST datasets. The models performances were assessed using AUC-ROC, with subgroup analyses for demographic, clinical, and imaging factors. Statistical comparisons were performed using DeLongs test. Gradient-based visualizations and probability distribution were further used for analysis. Results: The lesion-level model consistently outperformed the chest-region model across datasets. In internal validation, the lesion-level model achieved an AUC of 0.71(CI: 0.61-0.81), compared to 0.68(0.57-0.77) for the chest-region model. External validation showed similar trends, with AUCs of 0.90(0.87-0.92) and 0.81(0.79-0.82) on LUNA16 and NLST, respectively. Subgroup analyses revealed significant advantages for lesion-level models in certain histological subtypes (adenocarcinoma) and imaging conditions (CT manufacturers). Conclusion: Lesion-level models demonstrate superior classification performance, especially for external datasets and challenging subgroups, suggesting their clinical utility for precision lung cancer diagnostics.

A modern model release reports scores on 40+ benchmarks and the same evaluations were run many more times before it: to track training progress, compare design choices, and select the checkpoint for the release. But do we need to run every eval? We compile a public score matrix of 84 frontier models on 133 benchmarks (2,604 cells, 23.3% filled) and find it is approximately rank-2: a model's scores across all 133 benchmarks are largely determined by just two numbers. We confirm this in two ways: scores hidden from the matrix are best recovered using two factors, and two factors already explain over 90% of the variation among models on the benchmarks they share. Building on this, we design BenchPress: a logit-space rank-2 matrix completion method that recovers held-out scores to within 4.6 points, and a confidence layer that says when each prediction can be trusted. Using BenchPress, we find a subset of five benchmarks {GPQA-D, HLE, Codeforces, MMLU-Pro, ARC-AGI-1} that can recover the rest of a model's public scorecard to within 3.93 points. For a tighter inference budget, a cheaper set {GPQA-D, MMLU-Pro, Aider Polyglot, MATH-500, AIME 2026} can predict a model's evals to within 4.55. We release the score matrix, the BenchPress code, and an interactive tool that predicts any model's score on any benchmark.