GPT-5.3 Codex
#3Terminal Bench 2.0
by OpenAI
+
+
+
+
About
GPT-5.3 Codex, released by OpenAI in February 2026, is a coding-specialized model targeting software engineering workflows within agentic coding pipelines. It continues the Codex line's focus on professional developer tooling, with improvements designed around the automated coding workflows that have become central to AI-assisted software development.
+
+
+
+
Timeline
ReleasedFeb 5, 2026
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
1 benchmarks
Average Score
64.7%
Best Score
64.7%
High Performers (80%+)
0Top Categories
Coding
64.7%
+
+
+
+
All Benchmark Results for GPT-5.3 Codex
Complete list of benchmark scores with detailed information
| Terminal Bench 2.0 | Coding | 64.70 | 64.7% | Unverified |