minidev-pg

9 runs

The runs of this benchmark

One row per CLI run: the audit writes one second statement per question per run, so a prediction file is a run. Every benchmark is indexed a level up.

run date engine question set question set digest
gpt-35-turbo 2026-09-14T12:52:24.461204+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
gpt-35-turbo-instruct 2026-09-14T12:51:43.767965+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
gpt-4 2026-09-14T12:54:31.942106+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
gpt-4-32k 2026-09-14T12:53:00.424166+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
gpt-4-turbo 2026-09-14T12:53:37.264547+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
meta-llama-3-70b-instruct-2 2026-09-14T12:51:43.767965+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
meta-llama-3-8b-instruct-2 2026-09-14T12:57:46.865690+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
mistralai-mixtral-8x7b-instru-4 2026-09-14T12:55:37.302221+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
phi-3-medium-128k-instruct-1 2026-09-14T12:56:44.023614+00:00 postgresql https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab

Data and credit

The audited question sets are BIRD Mini-Dev and BIRD dev, both licensed under CC BY-SA 4.0. This site shows their question text, evidence text and gold SQL as they ship, beside results this project measured. The rest of the site is this project's own work under Apache-2.0, and NOTICE is the precise list of which files carry which.