A capability-driven benchmark of 400 bilingual real-world tasks shows current proactive agents fail >50% of the time, with framework architecture impacting performance more than base model choice.
Introducing claude opus 4.6
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2roles
baseline 1polarities
baseline 1representative citing papers
Claw-Eval is a new trajectory-aware benchmark for LLM agents that records execution traces, audit logs, and environment snapshots to evaluate completion, safety, and robustness across 300 tasks, revealing that opaque grading misses 44% of safety issues.
citing papers explorer
-
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
A capability-driven benchmark of 400 bilingual real-world tasks shows current proactive agents fail >50% of the time, with framework architecture impacting performance more than base model choice.
-
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Claw-Eval is a new trajectory-aware benchmark for LLM agents that records execution traces, audit logs, and environment snapshots to evaluate completion, safety, and robustness across 300 tasks, revealing that opaque grading misses 44% of safety issues.