第16位
Janitor AI
66C/O スコア
Illustrative preview: in this staging dataset Janitor AI reads strongest on narrative initiative and weakest on delayed recall under methodology v0.1.
重大な弱点 二点
- Illustrative record: delayed recall scored 55/100 in the staging scenario set.
- Illustrative record: local price stability scored 60/100 in the staging scenario set.
どんな人に向くか
- 向いている場合
- Readers weighting narrative initiative above the other criteria.
- 向いていない場合
- Readers who need verified production evidence rather than a staging preview.
試験項目
| 項目 | 結果 |
|---|---|
| Conversation quality | 66 |
| Local language and culture | 63 |
| Continuity and memory | 63 |
| Price and value | 65.8 |
| Product usability and reliability | 66 |
| Character and roleplay | 72.3 |
カテゴリー別スコア
| カテゴリー | C/O スコア |
|---|---|
| 総合 | 66 |
| 関係性 | 65.1 |
| ロールプレイ | 72.4 |
| 記憶 | 61.3 |
| 価格対効果 | 67.1 |
記憶のタイムライン
- continuity 65/1002026-08-15
- contradiction-resistance 63/1002026-08-15
- delayed-recall 55/1002026-08-15
- memory-controls 63/1002026-08-15
- relationship-continuity 69/1002026-08-15
現地語での観察結果
- local-language-performance: 63/100 (Illustrative staging scenario result recorded on the published 0-100 scale.)
価格と有料化の観察
| 試験した料金プラン | paid-standard |
|---|---|
| 観測価格 | ¥2,300 |
| 無料枠の上限 | 14 messages per day |
| 観測日 | 2026-08-12 |
代替候補 三件
- Nomi 79.2
- Character.AI 78.2
- Kindroid 77.2
リサーチ
方法と日付
方法 v0.1 に基づき 2026-08-24 に算出しました。
訂正
以下は記録に保存された英語の原文で、翻訳していません。
- 2026-08-24 app: apps — A destination may only be published once it has been resolved, not assumed. (Edition-specific official destinations assumed → Each edition points at the same verified official entry point until Task 7 verifies edition-specific destinations; スコア変動なし)
- 2026-08-23 price: prices/kr — Price facts must carry the date they were observed so staleness is visible. (Korean tier prices recorded without a stated observation date → Every Korean price observation carries an explicit 2026-08-12 observation date; スコア変動なし)
- 2026-08-22 methodology: 0.1 — The published weight table needed an unambiguous definition before any score was calculated. (Overall product/local-language component described as a single dimension → Overall product/local-language component is the mean of product reliability and local-language performance; スコア変動あり)