Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and Misses — AI benchmark

Jannatul Shefa, Alejandro Salado, Paul Wach, Taylan G. Topcu/Two Truths and A Lie? Benchmarking Off-the-Shelf LLMs for Requirements Quality Assessment: Performance, False Alarms, and MissesUnknown

Requirements engineering (RE) governs the quality of everything downstream in systems engineering (SE); defective requirements that survive review cycles propagate into design rework, schedule delays, and cost overruns. Because requirements are often written in natural language, recent advances in generative AI have raised expectations that large language models (LLMs) can absorb requirement quality assessment, a task otherwise slow and human expertise-intensive. Yet empirical evidence on whether LLMs can be trusted to do so remains scarce. This study presents the first benchmarking analysis of off-the-shelf LLM performance for requirement quality evaluation. Against an expert-derived ground truth built on INCOSE quality criteria, we evaluate ten models spanning two families (OpenAI and Anthropic) and five generations each, across one hundred independent runs, two requirement sets, and five sampling temperatures. Four contributions follow. First, we quantify a strongly asymmetric error profile: across all models and runs, the best-performing Anthropic model detects a median of only 47% of expert-identified issues while false-flagging 11%. Second, performance degrades significantly where SE judgment is required, as necessity and correctness issues are almost always missed. Third, generational progress is non-monotonic, so newer models cannot be assumed better. Fourth, this error behavior shifts only modestly and non-monotonically across sampling temperatures, indicating characteristic model deficiencies rather than inherent stochasticity. Off-the-shelf LLMs are therefore not yet trustworthy autonomous evaluators. Findings also warrant caution for Agentic AI developers: orchestrating these LLM modules in specialized architectures risks compounding these deficiencies rather than correcting them. Their defensible near-term role is human-in-the-loop decision support.

benchmark

Stars0

Forks0

HF Downloads—30d

Last commit—

Refreshed6h ago

Project healthUnknownNo activity data.

Production readinessResearch / EarlyBest for exploration and prototyping.

Risk notesUnknown licenseVerify license before production use.

AgentHub Score

55 / 100

Composite score from 6 signals. How we score →

Active project

55Score

Growth

40C

Activity

30C

Documentation

70C+

Maturity

45C

Community

42C

Production

58C

GitHub stars · 0 days observed0 not enough history

snapshots

not enough history

Repository activity · 0 days observednot enough history from pushed_at

inactivepushed

not enough history

Practical assessment

Should you use it?

✓ Best for

Research and experimentation
Prototype development
Learning agentic patterns

◎ Strengths

Active community
Open source
Well-documented API

✕ Not ideal for

Untested at scale without validation
Teams without AI/ML expertise

⚠ Watch-outs

Review changelog before updating
Verify license for commercial use

Technical details

What's inside

Language—

License—

Sourcearxiv

Open source✗ No

Commercial use—

Docs—

Demo—

PaperarXiv ↗

AgentHub Score

Score 55/100

Below average

Alternatives

RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems

0 · benchmark

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

0 · benchmark

AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation

0 · benchmark

FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents

0 · benchmark

55 Compare all →

Recent activity

Latest commit ——

Indexed by AgentHub crawler6h ago

Monitor for new releasesongoing