RUN / #0013已取消

运行 #13

模型：Sol、Gemini。比较模式：access_path；差异字段：adapter_kind、cli_version。创建于 2026年8月29日 16:43。

原始报告 JSON ↗完整事件 JSONL 返回运行索引

gpt-5.6-sol

Sol

codex_cli · text综合得分 / 100 · 越高越好

50.00

gemini-2.5-pro

Gemini

gemini_cli · text综合得分 / 100 · 越高越好

0.00

资源效率

分别列出准确率、每正确等价题 Token、估算费用和生成耗时。费用采用运行时冻结的价格快照。

指标	Sol	Gemini
准确率 `越高越好`	50.00	0.00
Token / 正确等价题 `越低越好`	19,331	—
费用 / 正确等价题 `USD · 估算`	不可估算	不可估算
模型生成耗时 P95 `越低越好`	—	—
累计 Token `已记录题数`	115,9846/12 题	—0/12 题

能力维度

加权得分

SolGemini

分类得分

0—100

能力维度	Sol	Gemini
基础查询	100.00	0.00
复杂管道	0.00	0.00
子查询	100.00	0.00
窗口函数	25.00	0.00
聚合分析	0.00	0.00
连接语义	100.00	0.00

逐题结果（12）

展开案例可查看模型摘要、SQL、错误和原始案例 JSON。

案例	Sol	Gemini
基础筛选与排序 `basic_filter_sort`	100.00	0.00
多表连接品类收入 `multi_join_category_revenue`	100.00	0.00
保留零订单客户 `left_join_zero_orders`	100.00	0.00
相关子查询分群均值 `correlated_segment_average`	100.00	0.00
从未完成订单客户 `not_exists_customers`	100.00	0.00
每品类收入前三商品 `top3_products_per_category`	100.00	0.00
月收入与累计收入 `monthly_running_revenue`	—	0.00
月收入环比增长 `monthly_mom_growth`	—	0.00
高于平均累计消费客户 `above_average_customer_spend`	—	0.00
渠道支付状态金额 `payment_status_by_channel`	—	0.00
品类退货率 `category_return_rate`	—	0.00
每单最新成功支付 `latest_successful_payment`	—	0.00

基础筛选与排序basic_filter_sort

Sol

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

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

STATUScompletedGEN—msEXEC234.1956670024956ms

上下文、请求与日志原始 JSON ↗

Gemini

Gemini 退出码 41: Please set an Auth method in your $PROJECT_ROOT/var/cli-homes/gemini/3/.gemini/settings.json or specify one of the following environment variables before running: GEMINI_API_KEY, GOOGLE_GENAI_USE_VERTEXAI, GOOGLE_GENAI_USE_GCA

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

多表连接品类收入multi_join_category_revenue

Sol

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

SELECT
  p.category AS 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,
  category ASC

STATUScompletedGEN—msEXEC293.5409579986299ms

上下文、请求与日志原始 JSON ↗

Gemini

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

保留零订单客户left_join_zero_orders

Sol

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。

SELECT
  c.customer_id,
  c.customer_name,
  COUNT(DISTINCT 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

STATUScompletedGEN—msEXEC222.6438750003581ms

上下文、请求与日志原始 JSON ↗

Gemini

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

相关子查询分群均值correlated_segment_average

Sol

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。

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 o2.customer_id = c2.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 o.customer_id = c.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 o3.customer_id = c3.customer_id
    WHERE
      o3.status = 'completed' AND c3.segment = c.segment
  )
ORDER BY
  o.total_amount DESC,
  o.order_id ASC

STATUScompletedGEN—msEXEC234.37312500027474ms

上下文、请求与日志原始 JSON ↗

Gemini

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

从未完成订单客户not_exists_customers

Sol

返回从未有已完成订单的客户，并按 customer_id 升序排列。

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

STATUScompletedGEN—msEXEC201.70074999987264ms

上下文、请求与日志原始 JSON ↗

Gemini

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

每品类收入前三商品top3_products_per_category

Sol

统计完成订单中各商品的净销售额，并用 ROW_NUMBER 选出每个品类净销售额最高的恰好前三个商品；同额时按 product_id 升序排名。

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

STATUScancelledGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

Gemini

STATUSfailedGEN—msEXEC—ms

上下文、请求与日志原始 JSON ↗

运行配置

字段来自运行创建时冻结的快照。

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 sha25670edf38add6526d12da760c4c62e6c6ff3d028636845367c13931a8915762252

report schemarun-report-v1

attempts1