PawBench

A benchmark for evaluating LLM × harness performance.

agentscope-ai/PawBench

View on GitHub ↗

A benchmark for evaluating LLM × harness performance.

PawBench grew +5.8% in the last 30 days, ranks 620th of 872 in Evaluation & Guardrails, last commit 110 days ago.

Star trajectory

82 days tracked
2026-08-31128 stars today2026-11-22
Momentum

+5.8% in 30d, above the Evaluation & Guardrails median of +1.4%.

Maintenance

Last commit 110 days ago, staler than the median of 15d.

How it compares in Evaluation & Guardrails

PawBench
128
stars
+5.8% 30d
commit 110 days ago
Evaluation & Guardrails median
235
stars
+1.4% 30d
commit ~15d ago
Leader · impeccable
114.7k
stars
+0.0% 30d
commit today

Ranked 620th of 872 by stars.

Ranked by shared tags, then keywords, then stars

Where PawBench sits

Hover or focus a node for details. Click to open it.

  • This repo
  • Related repo
  • Tag or category
  1. Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in…

    +13.4k (+40%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Evaluation & Guardrails

  2. The elegant testing framework for PHP developers and AI agents.

    +39 (+0.3%) in 30d · Committed today · PHP · MIT

    Shares Evaluation & Guardrails

  3. Multi-tier framework for evaluating AI agent skills and plugins with quality gates, security scanning, harness…

    +3.8k (+634%) in 30d · Committed today · Python · Apache-2.0

    Shares Evaluation & Guardrails

  4. AI API 中转站推荐与评测:中转站排行榜、中转站检测、Claude / GPT / Gemini 中转站对比 · AI API relay rankings · Folkbench Switch for Claude…

    +633 (+23%) in 30d · Committed today · TypeScript · Other license

    Shares Evaluation & Guardrails

  5. A contract-driven gRPC regression harness for AI coding agents, with human-approved baselines. Snapshot the…

    +1.8k (+133%) in 30d · Committed 26d ago · Go · MIT

    Shares Evaluation & Guardrails

  6. Official Repository for QuantHarness

    +24 (+0.8%) in 30d · Committed 95d ago · HTML · MIT

    Shares Evaluation & Guardrails

  7. τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

    +200 (+8.7%) in 30d · Committed yesterday · Python · MIT

    Shares Evaluation & Guardrails

  8. A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance…

    +98 (+4.8%) in 30d · Committed 12d ago · TypeScript · MIT

    Shares Evaluation & Guardrails

  9. ADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed…

    +69 (+3.3%) in 30d · Committed 2d ago · Python · Apache-2.0

    Shares Evaluation & Guardrails

  10. Deterministic guardrails that don't break agents

    +46 (+2.9%) in 30d · Committed today · Rust · MIT

    Shares Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
7
Forks
24
Watchers
1
Open issues
5
Releases
0
Created
2026-05-15
Stars this week
+0

You've seen where PawBench stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain PawBench?

Claim this page to add your own call-to-action.

Claim this page