Model comparison
GPT-5.3 Codex vs Hy4 preview
GPT-5.3 Codex and Hy4 preview score almost the same on the Noometry Index (45.8 vs 45.3), so choose on price, context window or the category you care about most.
Last verified . 1 shared benchmarks.
TencentSummary
- They share 1 benchmark with published results for both. GPT-5.3 Codex scores higher in 0 categories and Hy4 preview in 1 category; one gap is clear of the uncertainty.
- Hy4 preview is cheaper at $0.75 / $2.25 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- Hy4 preview accepts more context: 1.05M tokens versus 400K.
- Hy4 preview has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | Hy4 preview | |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 45.8 | 45.3 |
| Released | 2026-02-05 | 2026-08-28 |
| Weights | Proprietary | Open |
| Context window | 400K | 1.05M |
| Max output | 128K | 64K |
| Input $ / M tokens | $1.75 | $0.75 |
| Output $ / M tokens | $14 | $2.25 |
| Results tracked | 8 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
GPT-5.3 Codex: 48.6 (#56), Hy4 preview: 51.6 (#38)
| Benchmark | GPT-5.3 Codex | Hy4 preview |
|---|---|---|
| LMArena WebDev | 1409 | 1632 |
| SWE-bench Verified | 74.8% | — |
| WeirdML | 79.3% | — |
| ALE-Bench | 1,655 | — |
Agentic & Tool Use Not comparable
GPT-5.3 Codex: 48.0 (#9), Hy4 preview: —
| Benchmark | GPT-5.3 Codex | Hy4 preview |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Hy4 preview: 31.9 (#79)
| Benchmark | GPT-5.3 Codex | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | — | 68.2% |
| Epoch Capabilities Index | 156.77 | — |
Math Not comparable
GPT-5.3 Codex: —, Hy4 preview: 55.7 (#42)
| Benchmark | GPT-5.3 Codex | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
Frequently asked questions
Is GPT-5.3 Codex better than Hy4 preview?
GPT-5.3 Codex and Hy4 preview score almost the same on the Noometry Index (45.8 vs 45.3), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.3 Codex or Hy4 preview?
Hy4 preview is cheaper. It lists at $0.75 per million input tokens and $2.25 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 400K.
How many benchmarks do GPT-5.3 Codex and Hy4 preview share?
1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Hy4 preview has 3.