Entities · Models
Claude Opus 4.7
27 articles tagged with this entity.
-
Reconfigurable Radiology Labels Without Relabeling
-
Harnessing Code Agents for Automatic Software Verification
-
Benchmarking API Drift in LLM-Generated Quantum Code Across Successive SDK Versions
-
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
-
A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks
-
Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds
-
Claude Helped a Hacker Find a Way to Issue Tickets to Almost Every US Music Festival
-
OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
-
Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon
-
Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study
-
NormAct: A Benchmark for Hidden Social Norm Compliance in Embodied Planning
-
When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
-
GLM-5.2: Built for Long-Horizon Tasks
-
Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models
-
Embedded Arena: Iterative Optimization via Hardware Feedback
-
Scaffold Effects on GAIA: A Controlled Comparison
-
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
-
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle
-
Evaluation of LLMs for Mathematical Formalization in Lean
-
Frontier Lag: A Bibliometric Audit of Capability Misrepresentation in Academic AI Evaluation
-
SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers
-
Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
-
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
-
Anthropic Unveils Claude Opus 4.8, a New, More Powerful Model
-
ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM
-
LLM-driven design of physics-constrained constitutive models: two agents are better than one
-
MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence