'bench' 검색 결과

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

When the user requests information about academic benchmarks, datasets, or research papers, particularly in machine learning, deep learning, or logical reasoning domains. This skill enables systematic research of academic benchmarks by searching web sources, downloading and analyzing arXiv papers, extracting key metadata (number of tasks, training availability, difficulty levels), and compiling comparative summaries. It triggers on requests involving dataset comparisons, benchmark analysis, or academic paper research for table creation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

This skill details how to conduct cloud security audits using Center for Internet Security benchmarks for AWS, Azure, and GCP. It covers interpreting CIS Foundations Benchmark controls, running automated assessments with tools like Prowler and ScoutSuite, remediating failed controls, and maintaining continuous compliance monitoring against CIS v5 for AWS, v4 for Azure, and v4 for GCP.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

테스트를 먼저 작성하는 Go 개발을 돕습니다. 여러 사례 검증, HTTP 응답 확인, 성능 측정, 입력 자동 생성 검사와 커버리지 확인을 다룹니다.

• 테스트를 먼저 작성하는 Go 개발
• 정상 및 오류 테스트 사례 보완
• 처리 시간과 메모리 할당량 비교

점수가 매겨진 경쟁사 자료를 시장 지도, 비교표, 차별화 여지와 우선 실행안을 담은 보고서로 정리합니다. 경영진 보고와 팀의 경쟁 전략 결정에 활용합니다.

• 경영진·이사회용 경쟁 현황 보고
• 완성된 경쟁사 프로필 통합
• 차별화 여지와 경쟁 위협 검토

현재 성능 측정, 가설별 변경안 비교, 정확성 검증으로 최적화를 진행합니다. 시간과 비용 한도 안에서 가장 빠르고 안전한 안을 고르고 재실행 절차를 남깁니다.

• 느린 작업을 측정하며 속도 개선
• 같은 입력 조건에서 구현안 비교
• 응답 시간, 처리량, 실행 비용 평가

claude-flow v3의 시작 시간, 검색 속도와 메모리 사용량을 측정해 개선 목표 달성 여부를 검증합니다. 지속적인 성능 감시와 저하 감지, 최적화 방안 검토도 지원합니다.

• v3 최적화 전후의 성능을 비교합니다
• 검색 속도와 메모리 사용량을 평가합니다
• 지속적으로 성능 저하를 감지합니다

Measure throughput, response times, and resource use for systems and groups of agents. Use baseline comparisons, load tests, and performance criteria to identify slowdowns, assess behavior under pressure, and summarize results with recommendations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing performance before and after a code change
• Finding system limits through increasing load
• Checking coordination and load balancing across agents

Evaluate and improve the policy instructions that guide an AI agent using scored coding tasks. Run a learning cycle to compare candidates, or use the default dry run to inspect tasks and estimated costs without model calls.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Improving agent policies against a scored task set
• Estimating learning costs before running models
• Comparing candidates on held-out evaluation tasks

Measure and optimize claude-flow v3 startup, search, attention processing, and memory use. Compare benchmarks against performance targets, track changes over time, and identify regressions to guide further optimization.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare performance before and after v3 optimization
• Evaluate vector search speed and memory use
• Track performance regressions over time

Benchmark how CodeGraph affects an agent investigating a real codebase. Choose a version, language, repository, and execution mode, then compare cost, tool calls, file reads, and answer correctness with and without CodeGraph.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Evaluating a local development build
• Auditing a published CodeGraph version
• Comparing investigation cost and file reads

Design evaluation tasks that check whether agents actually complete work. Define requests, simulated user behavior, starting conditions, and verifiable success criteria, then plan difficulty levels, training-data leakage checks, and ongoing maintenance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating evaluation tasks for real business workflows
• Reviewing success criteria and verification logic
• Designing checks for evaluation data leakage into training

Plan and audit HypoGeniC workflows that use language models to propose patterns from labeled text. Check configurations, dataset splits, cost limits, and saved predictions while keeping candidate hypotheses separate from scientific confirmation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing task settings before a HypoGeniC run
• Checking duplicates across training and test data
• Estimating token and cost limits before model calls

Check release readiness inside the herdr repository by comparing changes since the base release with upcoming release notes and documentation. Review CLI descriptions, issue references, checks, and benchmarks, then report readiness.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check release notes against changes since the base release
• Review upcoming documentation before a release
• Inspect issue references that release CI will close

Review findings, drafts, assessments, and reports left by different work desks in a shared folder. Use each desk’s journal for context, then summarize the current state and highlight items that need attention.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review shared outputs at the start of a session
• Check another desk’s findings and context
• Review work before handing it to another desk

Add a CUDA/C++ GPU operation to sgl-kernel using AOT, meaning compilation before use. Follow the implementation through PyTorch registration, Python API exposure, SGLang integration, correctness tests, and benchmarks that account for cache reuse.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a CUDA/C++ operation to sgl-kernel
• Registering an operation with PyTorch and exposing a Python API
• Testing numerical results and invalid inputs

Review SGLang Cookbook pull requests for configuration errors, documentation mismatches, benchmark issues, and broken links. Get findings for each file and an overall recommendation on whether to approve, request changes, or block the contribution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a new model's Cookbook contribution
• Checking documentation against generated launch commands
• Checking benchmark definitions and measurement consistency

Explain portfolio performance by separating the effects of sector allocation, stock selection, market factors, and timing. Compare results with a benchmark, assess risk-adjusted returns, and prepare a report showing where excess returns came from.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explaining returns above or below a benchmark
• Separating sector allocation and stock-selection effects
• Assessing market exposure and trading timing

Analyze social media post data to calculate engagement, click rates, and estimated returns on advertising spend. Compare results with supplied platform benchmarks, identify strong and weak posts, and generate recommendations for improving campaign performance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review social campaign performance
• Identify posts with strong or weak engagement
• Estimate advertising returns and interaction costs

Create, update, run, and debug shell-based performance scenarios for the but CLI. It separates repository setup from the operation being measured, uses Hyperfine for timing, and guides focused validation and inspection of test output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a performance scenario for a but CLI operation
• Update repository fixtures for an existing benchmark
• Run a short benchmark for one scenario

Turn a broad robotics research direction into ranked ideas with concrete benchmarks and simulation plans. The workflow combines literature review, novelty checks, and external critique while accounting for hardware access, safety, evaluation metrics, and failure cases.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore research topics in manipulation or navigation
• Plan simulation studies before using physical robots
• Check novelty and feasibility of robotics ideas

Build Go services and command-line tools with clear interfaces, explicit error handling, and concurrent tasks using goroutines and channels. Use pprof to investigate performance, then check behavior with benchmarks, structured test cases, fuzzing, and race detection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implementing concurrent tasks with cancellation and error handling
• Building gRPC or REST services and command-line tools
• Investigating Go performance with pprof and benchmarks

Run concurrent Omnigent conversations with real hosts and runners while replacing the LLM with a zero-latency mock. Read the generated report to explain response-time distributions, throughput, and failures, helping assess Omnigent's own processing overhead.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Measuring performance with concurrent hosts
• Studying latency as conversation history grows
• Comparing throughput and failures under load