GPT-5.3 Codex vs Step-3.5-Flash: Specs & Benchmark Comparison
| Characteristic | GPT-5.3 Codex | Step-3.5-Flash |
|---|---|---|
| Company | OpenAI | StepFun |
| Release Date | February 5, 2026 | February 1, 2026 |
| Parameters | — | 196B |
| Multimodal | Yes | Yes |
| Context (input) | 400K | 66K |
| Context (output) | 128K | 8K |
| Input Price / 1M | $1.75 | $0.10 |
| Output Price / 1M | $14.00 | $0.40 |
| Average Score | 0.7 | 0.8 |
| Benchmarks | ||
| Terminal-Bench 2.0 | 0.8 | 0.4 |
Visual Benchmark Comparison
GPT-5.3 Codex
Step-3.5-Flash
Terminal-Bench 2.00.8 vs 0.4
0.8
0.4
Verdict
Both models show equal results — the choice depends on your specific use case.
Overall Performance
Both models show comparable average scores: GPT-5.3 Codex — 0.7, Step-3.5-Flash — 0.8.
API Cost
Step-3.5-Flash is 31.5x cheaper: input $0.10/1M vs $1.75/1M tokens.
Context Window
GPT-5.3 Codex supports a larger context: 400K vs 66K tokens.
Recency
Both models were released around the same time: 2/5/2026 and 2/1/2026.
More About These Models
Related Comparisons
The GPT-5.3 Codex and Step-3.5-Flash comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the GPT-5.3 Codex or Step-3.5-Flash page. See also the complete list of AI model comparisons.