TL;DR
GPT-4o mini (openai/gpt-4o-mini) appears in 2 published studies. 2024-07-19, GPT-4o mini and GPT-3.5 Turbo generating a portfolio JSON object: Pass for result. 2024-07-19, GPT-4o mini and GPT-3.5 Turbo generating a valid SQL query: Pass for result. Each result belongs to its own task, date and grading method.
- Exact tested ID
- openai/gpt-4o-mini
- Published studies
- 2
- Provider
- openai
Inspect this exact model
GPT-4o mini and GPT-3.5 Turbo generating a portfolio JSON object
GPT-4o mini: source evidence dated 2024-07-19.
- Result
- Pass
The displayed values belong to the identified model versions and this published task, with their original metric units.
How did this version perform on the job I need?
The first measured row below belongs to this model, not its provider's other models. Open that study to see the other arms and tested input.
2024-07-19: GPT-4o mini and GPT-3.5 Turbo generating a portfolio JSON objectSelect a model for the specific tested task. A profile with one study does not establish performance on other jobs.
Test a strategy with Aurora
Select a model for the specific tested task. A profile with one study does not establish performance on other jobs.
Test a strategy with AuroraKeep reporting dates and units beside the answer, and inspect its original citations.
GPT-4o mini and GPT-3.5 Turbo generating a portfolio JSON object
See the complete gpt-4o mini and gpt-3.5 turbo generating a portfolio json object
GPT-4o mini recorded Pass for result in the 2024-07-19 publication. 1 portfolio JSON task, 2 models, prompt count and run count not published in this excerpt.
| Published metric | Value |
|---|---|
| Result | Pass |
No matching rows. Clear the filter to see all records.
GPT-4o mini and GPT-3.5 Turbo generating a portfolio JSON object: read these measurements
View task, sample and measurement units
1 portfolio JSON task, 2 models, prompt count and run count not published in this excerpt
Generate a syntactically valid portfolio JSON object for an algorithmic trading strategy that can be used downstream.
Scoring
Author judgment: a pass means a valid portfolio object that worked downstream. A fail means no valid object.
Cost units
The article publishes no per-model cost for this test.
Time units
The article publishes no per-model timing.
GPT-4o mini and GPT-3.5 Turbo generating a valid SQL query
Open every published row
GPT-4o mini recorded Pass for result in the 2024-07-19 publication. 1 SQL generation task, 2 models, prompt count and run count not published in this excerpt.
| Published metric | Value |
|---|---|
| Result | Pass |
No matching rows. Clear the filter to see all records.
GPT-4o mini and GPT-3.5 Turbo generating a valid SQL query: read these measurements
View task, sample and measurement units
1 SQL generation task, 2 models, prompt count and run count not published in this excerpt
Generate a syntactically valid SQL query for a financial request and execute it against the database.
Scoring
Author judgment: a pass means a valid query with results that looked correct. A fail means no valid query.
Cost units
The article publishes no per-model cost for this test.
Time units
The article publishes no per-model timing.
No comments yet.