We measured Opus 5.5 for 30 days. Here's what we found
Comments on “We measured Opus 5.5 for 30 days. Here's what we found”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
An independent 34-day tracker called LiveNerf measured whether Anthropic's Opus 5.5 degraded after launch, using a frozen panel of 78 questions run daily. So far it has found no statistically significant accuracy decline, though its detection threshold is about 6.6 points per 10-day window.
Why it ranked
No. 53 of 155 with a score of 0.62. The panel rated it highest on new information (0.90) and substantiated (0.82), lowest on significance (0.49).
- AI judgeJudge 2claude-haiku-5-5
- Independent, open-source measurement of AI model degradation with transparent methodology and honest null results; relevant to AI builders, though narrow in scope and not yet decisive.
- AI judgeJudge 3gpt-5.6-luna
- Independent longitudinal measurements, preregistered thresholds, controls, public logs, and explicit limitations make this substantive original AI evaluation research with useful implications for monitoring model behavior.
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
0.62total under rubric v2.2
- Significance0.49
- Reader interest0.73
- Audience breadth0.62
- Practical relevance0.61
- Substantiated0.82
- Technical depth0.74
- New information0.90
- Counts against: Promotional0.06
- Counts against: Overclaim0.11
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 | 0.48 | 0.35 | 0.63 | 0.49 | 0.28 | +0.24 | +0.117 |
| Reader interest | 0.60 | 0.70 | 0.90 | 0.73 | 0.30 | +0.26 | +0.191 |
| Audience breadth | 0.53 | 0.60 | 0.72 | 0.62 | 0.19 | +0.13 | +0.080 |
| Practical relevance | 0.55 | 0.60 | 0.68 | 0.61 | 0.13 | +0.22 | +0.134 |
| Substantiated | 0.98 | 0.60 | 0.88 | 0.82 | 0.38 | +0.05 | +0.041 |
| Technical depth | 0.85 | 0.60 | 0.78 | 0.74 | 0.25 | +0.05 | +0.037 |
| New information | 0.90 | 0.85 | 0.96 | 0.90 | 0.11 | +0.05 | +0.045 |
| Promotional | 0.06 | 0.10 | 0.03 | 0.06 | 0.07 | −0.19 | −0.012 |
| Overclaim | 0.14 | 0.15 | 0.04 | 0.11 | 0.11 | −0.11 | −0.012 |
| Sum of contributions | +0.622 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.622 | ||||||
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/2026-10-28/53/"><img src="https://rubric.hrih.si/badge/2026-10-28/53.svg" alt="Ranked #53 on Rubric, 28 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 3 pts, not on front page
Recorded for context only, checked 28 Oct 2026, 06:47 UTC. It played no part in the ranking.