कंटेंट पर जाएँ
TakoAPI
स्किल्स पर वापस

agentbench

exe215 द्वारा

Coding Agents & IDEs
354clawskills.sh द्वारा बताए गए डाउनलोड
1स्टार
0व्यूज़
0 लाइकइस स्किल को लाइक करने के लिए साइन इन करें
—अभी तक कोई रेटिंग नहीं
आपकी रेटिंग

संक्षिप्त

Benchmark your OpenClaw agent across 40 real-world tasks.

विवरण

यह स्किल क्या करती है

AgentBench runs 40 real-world tasks across 7 domains to measure how well an OpenClaw agent performs. Tasks cover file creation, research, data analysis, multi-step workflows, memory, and error handling. Results are scored across four weighted layers and can be submitted to a public leaderboard.

Measures actual agent behavior across diverse real-world tasks rather than synthetic or code-only benchmarks, and the objective scoring layers (55% of total weight) can't be self-inflated.

इसे कब इस्तेमाल करें

  • Checking if a new agent config handles multi-step tasks reliably
  • Comparing agent performance before and after changing tool settings
  • Running a fast subset of tests to catch regressions after updates
  • Identifying which task domains an agent consistently underperforms in
  • Submitting scored results to the AgentBench public leaderboard

उदाहरण वर्कफ़्लो

इनपुट

User asks: /benchmark --fast

एजेंट
  1. 1

    Reads task.yaml files from the tasks/ directory, filtering to easy and medium difficulty tasks only

  2. 2

    Creates a timestamped run directory under agentbench-results/

  3. 3

    Executes each task in an isolated workspace, tracking tool calls, errors, and timing

  4. 4

    Scores each task across four layers: structural file checks, metrics analysis, behavioral self-evaluation, and output quality

  5. 5

    Generates results.json with integrity signature, report.md, and report.html in the run directory

आउटपुट

Overall score with per-domain breakdown, task detail table, and saved report files ready for review or submission

इंस्टॉलेशन

clawhub install exe215/agentbench

CLI कमांड चलाएँ, या प्रॉम्प्ट को Claude Code, Cursor, Codex या जो भी कोडिंग एजेंट आप इस्तेमाल करते हैं उसमें पेस्ट करें।

लिंक