diff --git a/index.html b/index.html index 7057289..6d7748a 100644 --- a/index.html +++ b/index.html @@ -40,7 +40,7 @@

How's GPT O1 Doing?

You can contribute your own tests, too! See the GitHub README for contributing instructions.

-

Tests are run every day at 1am PT. Last updated February 19, 2025.

+

Tests are run every day at 1am PT. Last updated February 20, 2025.

Made with ❤️ by the team at Roboflow.

@@ -58,12 +58,12 @@

How's GPT O1 Doing?

Response Time

-

Today, the average response time to receive results from our tests was 3.82 seconds per request.

+

Today, the average response time to receive results from our tests was 3.84 seconds per request.

This number only accounts for requests made by this application.

-

3.82 s

+

3.84 s

@@ -176,7 +176,7 @@

Prompt

Image

Image of the input into GPT-4

Result

-
I was
+
I was thinking earlier today that I have gone through, to use the lingo, eras of listening to each of Swift's Eras. Meta indeed. I started listening to Ms. Swift's music after hearing the Midnights album. A few weeks after hearing the album for the first time, I found myself playing various songs on repeat. I listened to the album

Test submitted by Roboflow

@@ -765,7 +765,7 @@

Zero Shot Classification

Of the last 7 tests, conducted daily, this test has passed 100% of the time.

-

Today's request cost $0.008

+

Today's request cost $0.01

diff --git a/results/2025-02-20.json b/results/2025-02-20.json new file mode 100644 index 0000000..0b6cbc2 --- /dev/null +++ b/results/2025-02-20.json @@ -0,0 +1,106 @@ +{ + "zero_shot_classification": { + "score": 1, + "success": true, + "price": 0.01012, + "pass_fail": "Pass", + "response_time": 7.093893051147461, + "result": "Toyota Camry" + }, + "count_fruit": { + "score": 0, + "success": false, + "price": 0.01545, + "pass_fail": "Fail", + "response_time": 9.379559993743896, + "result": "" + }, + "document_ocr": { + "score": 0, + "success": false, + "price": 0.013989999999999999, + "pass_fail": "Fail", + "response_time": 12.462197303771973, + "result": "I was thinking earlier today that I have gone through, to use the lingo, eras of listening to each of Swift's Eras. Meta indeed. I started listening to Ms. Swift's music after hearing the Midnights album. A few weeks after hearing the album for the first time, I found myself playing various songs on repeat. I listened to the album" + }, + "handwriting_ocr": { + "score": 0, + "success": false, + "price": 0.015529999999999999, + "pass_fail": "Fail", + "response_time": 11.129419326782227, + "result": "" + }, + "extraction_ocr": { + "score": 0, + "success": false, + "price": 0.013649999999999999, + "pass_fail": "Fail", + "response_time": 11.524913311004639, + "result": "Failed to produce a valid JSON output: " + }, + "math_ocr": { + "score": 0, + "success": false, + "price": 0.02113, + "pass_fail": "Fail", + "response_time": 10.938113451004028, + "result": "Failed to produce a valid JSON output: " + }, + "object_detection": { + "score": 0, + "success": false, + "price": 0.01584, + "pass_fail": "Fail", + "response_time": 17.056734323501587, + "result": "Failed to produce a valid JSON output: " + }, + "graph_understanding": { + "score": 0, + "success": false, + "price": 0.0157, + "pass_fail": "Fail", + "response_time": 8.02358365058899, + "result": "Failed to produce a valid JSON output: " + }, + "color_recognition": { + "score": 0, + "success": false, + "price": 0.0157, + "pass_fail": "Fail", + "response_time": 7.4073710441589355, + "result": "Failed to produce a valid JSON output: " + }, + "annotation_qa": { + "score": 0, + "success": false, + "price": 0.02135, + "pass_fail": "Fail", + "response_time": 31.52671527862549, + "result": "Failed to produce a valid JSON output: " + }, + "measurement": { + "score": 0, + "success": false, + "price": 0.01566, + "pass_fail": "Fail", + "response_time": 10.37532639503479, + "result": "Failed to produce a valid JSON output: " + }, + "easy_captcha": { + "score": 0, + "success": false, + "price": 0.01281, + "pass_fail": "Fail", + "response_time": 7.882266521453857, + "result": "" + }, + "easy_captcha_persuade": { + "score": 0, + "success": false, + "price": 0.013309999999999999, + "pass_fail": "Fail", + "response_time": 5.799127817153931, + "result": "" + } +} \ No newline at end of file