jwu323/FlowBench
FlowBench: Harbor dataset on Hugging Face with 300 tasks. Dataset ID: jwu323/FlowBench FlowBench is a tool-use benchmark for deterministic business operations workflows. Each task asks an agent to compose Python tools over synthetic customers, products, orders, returns, inventory, support tickets…
Tasks
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Required output: - /app/answer.txt must contain only the exact code. - Use integer arithmetic for currency and counts. Do not use…
- Task: For region NA, category A, months 202601-202603, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category B, months 202604-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category B, months 202604-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category A, months 202601-202603, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category C, months 202601-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category B, months 202601-202603, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category C, months 202602-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category D, months 202601-202605, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category A, months 202604-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category D, months 202601-202602, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category A, months 202603-202604, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category B, months 202605-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category C, months 202601-202604, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category C, months 202602-202604, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category B, months 202604-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category D, months 202603-202605, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category C, months 202601-202602, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category D, months 202601-202603, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category D, months 202603-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category A, months 202602-202605, identify the product id with the highest units sold. Report only the product id;…
- Task: For region APAC, category D, months 202601-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category B, months 202601-202604, identify the product id with the highest units sold. Report only the product id;…
- Task: For region LATAM, category C, months 202603-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region NA, category D, months 202602-202606, identify the product id with the highest units sold. Report only the product id;…
- Task: For region EU, category A, months 202602-202605, identify the product id with the highest units sold. Report only the product id;…
- Task: How many paid/refunded orders are in region NA, category A, from month 202601 through 202603? Report the count.
- Task: How many paid/refunded orders are in region NA, category B, from month 202604 through 202606? Report the count.
- Task: How many paid/refunded orders are in region APAC, category B, from month 202604 through 202606? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category A, from month 202601 through 202603? Report the count.
- Task: How many paid/refunded orders are in region NA, category C, from month 202601 through 202606? Report the count.
- Task: How many paid/refunded orders are in region EU, category B, from month 202601 through 202603? Report the count.
- Task: How many paid/refunded orders are in region APAC, category C, from month 202602 through 202606? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category D, from month 202601 through 202605? Report the count.
- Task: How many paid/refunded orders are in region NA, category A, from month 202604 through 202606? Report the count.
- Task: How many paid/refunded orders are in region EU, category D, from month 202601 through 202602? Report the count.
- Task: How many paid/refunded orders are in region APAC, category A, from month 202603 through 202604? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category B, from month 202605 through 202606? Report the count.
- Task: How many paid/refunded orders are in region EU, category C, from month 202601 through 202604? Report the count.
- Task: How many paid/refunded orders are in region NA, category C, from month 202602 through 202604? Report the count.
- Task: How many paid/refunded orders are in region EU, category B, from month 202604 through 202606? Report the count.
- Task: How many paid/refunded orders are in region APAC, category D, from month 202603 through 202605? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category C, from month 202601 through 202602? Report the count.
- Task: How many paid/refunded orders are in region NA, category D, from month 202601 through 202603? Report the count.
- Task: How many paid/refunded orders are in region EU, category D, from month 202603 through 202606? Report the count.
- Task: How many paid/refunded orders are in region APAC, category A, from month 202602 through 202605? Report the count.
- Task: How many paid/refunded orders are in region APAC, category D, from month 202601 through 202606? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category B, from month 202601 through 202604? Report the count.
- Task: How many paid/refunded orders are in region LATAM, category C, from month 202603 through 202606? Report the count.
- Task: How many paid/refunded orders are in region NA, category D, from month 202602 through 202606? Report the count.
- Task: How many paid/refunded orders are in region EU, category A, from month 202602 through 202605? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category A, from month 202601 through 202603? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category B, from month 202604 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category B, from month 202604 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category A, from month 202601 through 202603? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category C, from month 202601 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category B, from month 202601 through 202603? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category C, from month 202602 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category D, from month 202601 through 202605? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category A, from month 202604 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category D, from month 202601 through 202602? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category A, from month 202603 through 202604? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category B, from month 202605 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category C, from month 202601 through 202604? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category C, from month 202602 through 202604? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category B, from month 202604 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category D, from month 202603 through 202605? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category C, from month 202601 through 202602? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category D, from month 202601 through 202603? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category D, from month 202603 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category A, from month 202602 through 202605? Report the count.
- Task: How many unique customers placed paid/refunded orders in region APAC, category D, from month 202601 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category B, from month 202601 through 202604? Report the count.
- Task: How many unique customers placed paid/refunded orders in region LATAM, category C, from month 202603 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region NA, category D, from month 202602 through 202606? Report the count.
- Task: How many unique customers placed paid/refunded orders in region EU, category A, from month 202602 through 202605? Report the count.
- Task: For orders in region NA, category A, months 202601-202603: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region NA, category B, months 202604-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region APAC, category B, months 202604-202606: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category A, months 202601-202603: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region NA, category C, months 202601-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region EU, category B, months 202601-202603: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region APAC, category C, months 202602-202606: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category D, months 202601-202605: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region NA, category A, months 202604-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region EU, category D, months 202601-202602: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region APAC, category A, months 202603-202604: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category B, months 202605-202606: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region EU, category C, months 202601-202604: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region NA, category C, months 202602-202604: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region EU, category B, months 202604-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region APAC, category D, months 202603-202605: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category C, months 202601-202602: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region NA, category D, months 202601-202603: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region EU, category D, months 202603-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region APAC, category A, months 202602-202605: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region APAC, category D, months 202601-202606: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category B, months 202601-202604: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region LATAM, category C, months 202603-202606: compute each order's net USD revenue after loyalty discount and…
- Task: For orders in region NA, category D, months 202602-202606: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region EU, category A, months 202602-202605: compute each order's net USD revenue after loyalty discount and refunds,…
- Task: For orders in region NA, category A, months 202601-202603: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category B, months 202604-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category B, months 202604-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category A, months 202601-202603: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category C, months 202601-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category B, months 202601-202603: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category C, months 202602-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category D, months 202601-202605: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category A, months 202604-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category D, months 202601-202602: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category A, months 202603-202604: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category B, months 202605-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category C, months 202601-202604: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category C, months 202602-202604: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category B, months 202604-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category D, months 202603-202605: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category C, months 202601-202602: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category D, months 202601-202603: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category D, months 202603-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category A, months 202602-202605: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region APAC, category D, months 202601-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category B, months 202601-202604: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region LATAM, category C, months 202603-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region NA, category D, months 202602-202606: sum gross USD revenue and refund USD amounts, then report the refund…
- Task: For orders in region EU, category A, months 202602-202605: sum gross USD revenue and refund USD amounts, then report the refund…
150 more tasks.