拾拾穗数据工作室SQL 模型评测台

完成 · 2026年8月30日 03:53

运行 #14 评测报告

Sol，12 道题。综合得分为规则加权分，不是正确率。

比较条件存在差异：single_model。阅读模型间差距时必须保留这一前提。

逐题结果原始报告 JSON ↗事件 JSONL ↗
gpt-5.6-sol

Sol

综合得分 / 100
98.12
12题目数量
1每题尝试次数
0失败案例

样本边界：结论仅适用于此题库哈希、模型版本、适配器和参数快照。跨版本、跨运行稳定性需要独立复测。

得分与资源消耗

新 efficiency-v2 按业务结果正确题数归一；旧 efficiency-v1 保留综合得分 ÷ 100 的折算口径，两种指标不能混排。记录不完整时不估算单位正确题消耗。

指标Sol
综合得分
固定规则加权 / 100		98.12
Token / 归一单位19,753每得分折算题 · 12/12 题有记录
费用 / 归一单位
基于冻结价格；缺失不估		不可估算每得分折算题 · unavailable
生成耗时中位数
模型生成阶段		—P95 —

分项得分

分项为加权得分，不是业务结果正确率。

题目维度Sol
基础查询100.00
复杂管道96.25
子查询100.00
窗口函数96.25
聚合分析100.00
连接语义100.00

逐题结果

得分为全部计划尝试的均分，失败计入分母，未完成显示未知。展开可查看每次作答。

基础筛选与排序basic_filter_sort100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

查询 2026-01-01 起的已完成订单及客户名称，按订单总额降序、订单 ID 升序排列。

结果正确（页面派生）

SELECT
  o.order_id,
  c.customer_name,
  o.order_date,
  o.total_amount
FROM fact_orders AS o
JOIN dim_customers AS c
  ON o.customer_id = c.customer_id
WHERE
  o.status = 'completed' AND o.order_date >= CAST('2026-01-01' AS DATE)
ORDER BY
  o.total_amount DESC,
  o.order_id ASC
查看 A1 完整证据
多表连接品类收入multi_join_category_revenue100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

按商品品类汇总已完成订单的去重订单数与订单行净销售额，并按净销售额降序、品类升序排列。

结果正确（页面派生）

SELECT
  p.category,
  COUNT(DISTINCT o.order_id) AS order_count,
  SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS net_revenue
FROM fact_orders AS o
JOIN fact_order_items AS oi
  ON oi.order_id = o.order_id
JOIN dim_products AS p
  ON p.product_id = oi.product_id
WHERE
  o.status = 'completed'
GROUP BY
  p.category
ORDER BY
  net_revenue DESC,
  p.category ASC
查看 A1 完整证据
保留零订单客户left_join_zero_orders100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

列出所有客户及其已完成订单数，通过 LEFT JOIN 保留零订单客户，并按完成订单数降序、客户 ID 升序排列。

结果正确（页面派生）

SELECT
  c.customer_id,
  c.customer_name,
  COUNT(o.order_id) AS completed_order_count
FROM dim_customers AS c
LEFT JOIN fact_orders AS o
  ON c.customer_id = o.customer_id AND o.status = 'completed'
GROUP BY
  c.customer_id,
  c.customer_name
ORDER BY
  completed_order_count DESC,
  c.customer_id ASC
查看 A1 完整证据
相关子查询分群均值correlated_segment_average100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

返回金额高于其客户分群已完成订单平均金额的已完成订单，并按订单金额降序、订单 ID 升序排列。

结果正确（页面派生）

SELECT
  o.order_id,
  o.customer_id,
  c.segment,
  o.total_amount,
  (
    SELECT
      AVG(o2.total_amount)
    FROM fact_orders AS o2
    JOIN dim_customers AS c2
      ON c2.customer_id = o2.customer_id
    WHERE
      o2.status = 'completed' AND c2.segment = c.segment
  ) AS segment_avg_amount
FROM fact_orders AS o
JOIN dim_customers AS c
  ON c.customer_id = o.customer_id
WHERE
  o.status = 'completed'
  AND o.total_amount > (
    SELECT
      AVG(o3.total_amount)
    FROM fact_orders AS o3
    JOIN dim_customers AS c3
      ON c3.customer_id = o3.customer_id
    WHERE
      o3.status = 'completed' AND c3.segment = c.segment
  )
ORDER BY
  o.total_amount DESC,
  o.order_id ASC
查看 A1 完整证据
从未完成订单客户not_exists_customers100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

返回从未有已完成订单的客户，并按 customer_id 升序排列。

结果正确（页面派生）

SELECT
  c.customer_id,
  c.customer_name
FROM dim_customers AS c
WHERE
  NOT EXISTS(
    SELECT
      1
    FROM fact_orders AS o
    WHERE
      o.customer_id = c.customer_id AND o.status = 'completed'
  )
ORDER BY
  c.customer_id ASC
查看 A1 完整证据
每品类收入前三商品top3_products_per_category100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

汇总完成订单中各商品的净销售额，使用 ROW_NUMBER 按品类排名，并返回每个品类前三名商品。

结果正确（页面派生）

WITH product_revenue AS (
  SELECT
    p.category,
    p.product_id,
    p.product_name,
    SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS net_revenue
  FROM fact_order_items AS oi
  JOIN fact_orders AS o
    ON oi.order_id = o.order_id
  JOIN dim_products AS p
    ON oi.product_id = p.product_id
  WHERE
    o.status = 'completed'
  GROUP BY
    p.category,
    p.product_id,
    p.product_name
), ranked_products AS (
  SELECT
    category,
    product_id,
    product_name,
    net_revenue,
    ROW_NUMBER() OVER (PARTITION BY category ORDER BY net_revenue DESC, product_id ASC) AS rank_no
  FROM product_revenue
)
SELECT
  category,
  product_id,
  product_name,
  net_revenue,
  rank_no
FROM ranked_products
WHERE
  rank_no <= 3
ORDER BY
  category ASC,
  rank_no ASC
查看 A1 完整证据
月收入与累计收入monthly_running_revenue100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

按月汇总 2025 年已完成订单的净销售额，并使用按月份排序的 SUM 窗口计算累计收入。

结果正确（页面派生）

WITH monthly AS (
  SELECT
    STRFTIME(o.order_date, '%Y-%m') AS month,
    SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue
  FROM fact_orders AS o
  JOIN fact_order_items AS oi
    ON oi.order_id = o.order_id
  WHERE
    o.status = 'completed'
    AND o.order_date >= CAST('2025-01-01' AS DATE)
    AND o.order_date < CAST('2026-01-01' AS DATE)
  GROUP BY
    1
)
SELECT
  month,
  monthly_revenue,
  SUM(monthly_revenue) OVER (ORDER BY month ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS cumulative_revenue
FROM monthly
ORDER BY
  month ASC
查看 A1 完整证据
月收入环比增长monthly_mom_growth100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

按月汇总 2025 年完成订单的净销售额，并使用 LAG 计算环比百分比；首个有收入月份为 NULL。

结果正确（页面派生）

WITH monthly AS (
  SELECT
    STRFTIME(o.order_date, '%Y-%m') AS month,
    SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS monthly_revenue
  FROM fact_orders AS o
  JOIN fact_order_items AS oi
    ON oi.order_id = o.order_id
  WHERE
    o.status = 'completed'
    AND o.order_date >= CAST('2025-01-01' AS DATE)
    AND o.order_date < CAST('2026-01-01' AS DATE)
  GROUP BY
    1
), with_previous AS (
  SELECT
    month,
    monthly_revenue,
    LAG(monthly_revenue) OVER (ORDER BY month) AS previous_revenue
  FROM monthly
)
SELECT
  month,
  monthly_revenue,
  ROUND(100.0 * (
    monthly_revenue - previous_revenue
  ) / NULLIF(previous_revenue, 0), 2) AS mom_pct
FROM with_previous
ORDER BY
  month ASC
查看 A1 完整证据
高于平均累计消费客户above_average_customer_spend100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

返回累计已完成订单净消费高于有已完成订单客户平均累计净消费的客户，并按消费降序、客户 ID 升序排列。

结果正确（页面派生）

SELECT
  customer_id,
  customer_name,
  total_spend
FROM (
  SELECT
    customer_id,
    customer_name,
    total_spend,
    AVG(total_spend) OVER () AS avg_total_spend
  FROM (
    SELECT
      c.customer_id,
      c.customer_name,
      SUM(oi.quantity * oi.unit_price - oi.discount_amount) AS total_spend
    FROM fact_orders AS o
    JOIN fact_order_items AS oi
      ON oi.order_id = o.order_id
    JOIN dim_customers AS c
      ON c.customer_id = o.customer_id
    WHERE
      o.status = 'completed'
    GROUP BY
      c.customer_id,
      c.customer_name
  ) AS customer_spend
) AS customer_spend_with_avg
WHERE
  total_spend > avg_total_spend
ORDER BY
  total_spend DESC,
  customer_id ASC
查看 A1 完整证据
渠道支付状态金额payment_status_by_channel100.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 100.00

按渠道类型汇总支付成功、退款状态和支付失败的金额，并按渠道类型升序排列。

结果正确（页面派生）

SELECT
  c.channel_type,
  SUM(CASE WHEN p.status = 'paid' THEN p.amount ELSE 0 END) AS paid_amount,
  SUM(CASE WHEN p.status = 'refunded' THEN p.amount ELSE 0 END) AS refunded_amount,
  SUM(CASE WHEN p.status = 'failed' THEN p.amount ELSE 0 END) AS failed_amount
FROM fact_payments AS p
JOIN fact_orders AS o
  ON p.order_id = o.order_id
JOIN dim_channels AS c
  ON o.channel_id = c.channel_id
GROUP BY
  c.channel_type
ORDER BY
  c.channel_type ASC
查看 A1 完整证据
品类退货率category_return_rate92.50

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 92.50

分别按品类聚合完成订单的售出数量和退货数量，再计算四舍五入至 4 位的退货率，避免明细表直接联结导致重复计数。

结果正确（页面派生）

WITH sold_by_category AS (
  SELECT
    p.category,
    SUM(oi.quantity) AS sold_qty
  FROM fact_order_items AS oi
  JOIN fact_orders AS o
    ON o.order_id = oi.order_id
  JOIN dim_products AS p
    ON p.product_id = oi.product_id
  WHERE
    o.status = 'completed'
  GROUP BY
    p.category
), returned_by_category AS (
  SELECT
    p.category,
    SUM(r.return_qty) AS returned_qty
  FROM fact_returns AS r
  JOIN fact_order_items AS oi
    ON oi.order_id = r.order_id AND oi.line_no = r.line_no
  JOIN fact_orders AS o
    ON o.order_id = oi.order_id
  JOIN dim_products AS p
    ON p.product_id = oi.product_id
  WHERE
    o.status = 'completed'
  GROUP BY
    p.category
)
SELECT
  s.category,
  s.sold_qty,
  COALESCE(r.returned_qty, 0) AS returned_qty,
  ROUND(CAST(COALESCE(r.returned_qty, 0) AS DECIMAL(18, 3)) / NULLIF(s.sold_qty, 0), 4) AS return_rate
FROM sold_by_category AS s
LEFT JOIN returned_by_category AS r
  ON r.category = s.category
ORDER BY
  return_rate DESC,
  s.category ASC
查看 A1 完整证据
每单最新成功支付latest_successful_payment85.00

Sol

全部 1 次计划作答 · 结果正确（页面派生）

A1 · 完成 · 85.00

为每个有成功支付记录的订单返回最新一笔成功支付；paid_at 相同时选择 payment_id 较大的记录。

结果正确（页面派生）

SELECT
  order_id,
  payment_id,
  paid_at,
  amount
FROM (
  SELECT
    order_id,
    payment_id,
    paid_at,
    amount,
    ROW_NUMBER() OVER (PARTITION BY order_id ORDER BY paid_at DESC, payment_id DESC) AS rn
  FROM fact_payments
  WHERE
    status = 'paid'
) AS ranked_payments
WHERE
  rn = 1
ORDER BY
  order_id ASC
查看 A1 完整证据

配置与校验摘要

复测需使用对应的冻结配置和题库哈希。同一模型名不一定对应同一模型版本。

app_version0.1.0
attempts1
case_count12
duckdb_version1.5.5
output_contractquery-plan-v1
scorer_version1.0.0
sqlglot_version30.17.0
suite hash0a4a18b4374f510f5eff18b06272c30c3375e1f082ae405adc8ead7dd9c81556
bundle sha256b8f72f4f616f4077a37a7a180dc1dab0c2e9522dde02b1b42f1738b53c0abb99
report schemarun-report-v1
报告 JSON ↗题库版本评分方法