GPT-5.3 Terra
OpenAI
Parameters
—
Architecture
—
Released
—
License
—
Input Modalities
text
image
Output Modalities
text
About
No detailed description available for this model.
Benchmark Scores
| Benchmark | Score | Date | Standing |
|---|---|---|---|
|
Terminal Bench 2.1
coding_agent
|
96.45%
|
27.08.2026 |
#6/44
better than 88%
|
|
Agents' Last Exam
general_agent
|
50.31%
|
27.08.2026 |
#10/29
better than 61%
|
|
GDPVal-AA v2
general_agent
|
85.80%
|
27.08.2026 |
#16/38
better than 59%
|
|
DeepSWE 1.1
coding_agent
|
90.36%
|
27.08.2026 |
#9/34
better than 76%
|
|
Automation-Bench
general_agent
|
50.77%
|
27.08.2026 |
#10/27
better than 65%
|
What is a good Terminal Bench 2.1 score? What is a good Agents' Last Exam score? What is a good GDPVal-AA v2 score?
No comments yet
Be the first to share your thoughts!