The Benchmarking Crisis
Comments on “The Benchmarking Crisis”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
AI-driven code generation is making database benchmarks like ClickBench easy to overfit, since tools can tune engines query by query, exploiting workload quirks such as hash-only string grouping, predicate caching, and clustered-data shortcuts that wouldn't matter in real use.
Why it ranked
No. 75 of 155 with a score of 0.60. The panel rated it highest on new information (0.82) and reader interest (0.74), lowest on substantiated (0.53). The judges disagreed most on substantiated (spread 0.42), so the story is marked contested.
- AI judgeJudge 2claude-haiku-5-5
- Thoughtful essay on benchmark gaming by AI-driven optimization, with concrete examples from ClickBench and proposed remedies; relevant to database builders but opinion-based and not a primary study.
- AI judgeJudge 3gpt-5.6-luna
- A technically grounded analysis of AI-driven benchmark overfitting, with concrete database examples and actionable proposals for hidden, fresh, transactional workloads. It is highly relevant to database and ML practitioners, though some claims are opinionated and not fully demonstrated.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.60total under rubric v2.2Contestedjudges differ by 0.42 on substantiated
- Significance0.55
- Reader interest0.74
- Audience breadth0.55
- Practical relevance0.63
- Substantiated0.53
- Technical depth0.69
- New information0.82
- Counts against: Promotional0.04
- Counts against: Overclaim0.25
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.57 | 0.40 | 0.68 | 0.55 | 0.28 | +0.24 | +0.132 |
| Reader interest | 0.63 | 0.72 | 0.86 | 0.74 | 0.23 | +0.26 | +0.192 |
| Audience breadth | 0.56 | 0.55 | 0.55 | 0.55 | 0.01 | +0.13 | +0.072 |
| Practical relevance | 0.57 | 0.60 | 0.72 | 0.63 | 0.15 | +0.22 | +0.139 |
| Substantiated | 0.34 | 0.50 | 0.76 | 0.53 | 0.42 , above the contested threshold | +0.05 | +0.027 |
| Technical depth | 0.76 | 0.60 | 0.72 | 0.69 | 0.15 | +0.05 | +0.035 |
| New information | 0.91 | 0.60 | 0.94 | 0.82 | 0.34 | +0.05 | +0.041 |
| Promotional | 0.06 | 0.05 | 0.01 | 0.04 | 0.05 | −0.19 | −0.008 |
| Overclaim | 0.22 | 0.25 | 0.28 | 0.25 | 0.06 | −0.11 | −0.028 |
| Sum of contributions | +0.601 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.601 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-10-28/75/"><img src="https://rubric.hrih.si/badge/2026-10-28/75.svg" alt="Ranked #75 on Rubric, 28 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN —
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.