On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.
years
2026 7representative citing papers
EnterpriseClawBench is a benchmark for enterprise agents constructed from proprietary real-world sessions, with the reusable contribution being the construction and evaluation protocol rather than the data itself.
RNG-Bench evaluates MLLMs on hidden-observation reconstruction in non-Markov games, finds forgetting as the dominant error source, and shows fine-tuning on optimal rollouts improves performance with transfer to other benchmarks.
RealClawBench turns 281 real OpenClaw sessions into reproducible tasks that preserve the original distribution and shows the best of 14 models solves only 65.8 percent.
CPT is introduced as a pairwise reasoning-trace comparison stage that improves the reasoning-metacognition trade-off over standard SFT+RL pipelines across model scales.
RAMP evaluates 15 models on production-like serial workflows and reports completion rates collapsing from 100% to 20% with none finishing the full pipeline and costs varying by three orders of magnitude.
citing papers explorer
-
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
On 108 long-horizon real-world computer workflows, frontier agents complete at most 20.6% of tasks and fail mainly by losing hidden state, not by basic GUI control.
-
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
EnterpriseClawBench is a benchmark for enterprise agents constructed from proprietary real-world sessions, with the reusable contribution being the construction and evaluation protocol rather than the data itself.
-
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games
RNG-Bench evaluates MLLMs on hidden-observation reconstruction in non-Markov games, finds forgetting as the dominant error source, and shows fine-tuning on optimal rollouts improves performance with transfer to other benchmarks.
-
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
RealClawBench turns 281 real OpenClaw sessions into reproducible tasks that preserve the original distribution and shows the best of 14 models solves only 65.8 percent.
-
Enhancing LLM Metacognition via Cognitive Pairwise Training
CPT is introduced as a pairwise reasoning-trace comparison stage that improves the reasoning-metacognition trade-off over standard SFT+RL pipelines across model scales.
-
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems
RAMP evaluates 15 models on production-like serial workflows and reports completion rates collapsing from 100% to 20% with none finishing the full pipeline and costs varying by three orders of magnitude.
- PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows