Introducing GPT-5.3-Codex-Spark (OpenAI) 12 Feb 2026
- SWE-Bench Pro, xhigh 51.5
- Terminal-Bench 2.0 58.4
GPT-5.3-Codex-Spark
GPT-5.3-Codex-Spark.
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Feb 2026
GPT-5.3-Codex-Spark
Closed weights Small
No Epoch Capabilities Index score yet
- SlopCodeBench 8.16% #13 /14
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-Bench Pro | 51.5% | #62 of 77 | Model card | |
| SlopCodeBench | 8.16% | #13 of 14 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench 2.0 | 58.4% | #24 of 61 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.