# GPT-5.3 Codex vs Hy3

> GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 43.6 on the Noometry Index. Hy3 costs 21× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-3-codex-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.3 Codex scores higher in 1 category and Hy3 in 0 categories; one gap is clear of the uncertainty.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Codex | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 45.5 | 43.6 |
| Rank | 61 | 79 |
| Context | 400K | 262K |
| Input $/M | $1.75 | $0.13 |
| Output $/M | $14 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Codex: 48.5 (#51)
- Hy3: 46.6 (#60)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena WebDev | 1408 | 1509 |
| SWE-bench Verified | 74.8% | — |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 1465 |
| ALE-Bench | 1,655 | — |

## Agentic & Tool Use

- GPT-5.3 Codex: 47.8 (#9)
- Hy3: —

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |

## Reasoning

- GPT-5.3 Codex: —
- Hy3: 25.0 (#134)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| NYT Connections (extended) | — | 41.2% |
| LMArena Hard Prompts | — | 1449 |
| Epoch Capabilities Index | 156.84 | — |

## Math

- GPT-5.3 Codex: —
- Hy3: 37.4 (#98)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Math | — | 1475 |

## Knowledge

- GPT-5.3 Codex: —
- Hy3: 40.2 (#108)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Expert | — | 1461 |

## Multilingual

- GPT-5.3 Codex: —
- Hy3: 53.7 (#60)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1496 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1390 |
| LMArena Russian | — | 1435 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- GPT-5.3 Codex: —
- Hy3: 75.3 (#68)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1425 |

## Long Context

- GPT-5.3 Codex: —
- Hy3: 44.1 (#70)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1443 |

## Writing & Preference

- GPT-5.3 Codex: —
- Hy3: 62.5 (#75)

| Benchmark | GPT-5.3 Codex | Hy3 |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1399 |
| LMArena Multi-Turn | — | 1436 |

## FAQ

### Is GPT-5.3 Codex better than Hy3?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 43.6 on the Noometry Index. Hy3 costs 21× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.3 Codex or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.

### Is GPT-5.3 Codex or Hy3 better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 46.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.3 Codex and Hy3 share?

1 benchmark has published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Hy3 has 17.