# GPT-5.1-Codex vs Hy3

> Hy3 is the stronger model overall, scoring 44.2 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-1-codex-vs-hy3
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5.1-Codex scores higher in 0 categories and Hy3 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 30.3.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.1-Codex | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 38.6 | 44.2 |
| Rank | 186 | 79 |
| Context | 400K | 262K |
| Input $/M | $1.25 | $0.13 |
| Output $/M | $10 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.1-Codex: 41.9 (#116)
- Hy3: 46.8 (#63)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena WebDev | 1337 | 1508 |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena Coding | — | 1464 |
| ALE-Bench | 1,245 | — |

## Agentic & Tool Use

- GPT-5.1-Codex: 38.0 (#33)
- Hy3: —

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| METR Time Horizons | 70.8% | — |

## Reasoning

- GPT-5.1-Codex: —
- Hy3: 26.1 (#136)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| NYT Connections (extended) | — | 41.2% |
| LMArena Hard Prompts | — | 1447 |

## Math

- GPT-5.1-Codex: 30.3 (#235)
- Hy3: 40.1 (#93)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| ProofBench | 9% | — |
| LMArena Math | — | 1475 |

## Knowledge

- GPT-5.1-Codex: —
- Hy3: 40.8 (#114)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena Expert | — | 1460 |

## Multilingual

- GPT-5.1-Codex: —
- Hy3: 53.5 (#65)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena Non-English | — | 1426 |
| LMArena Chinese | — | 1493 |
| LMArena French | — | 1461 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Russian | — | 1432 |
| LMArena Spanish | — | 1456 |

## Instruction Following

- GPT-5.1-Codex: —
- Hy3: 75.1 (#70)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena Instruction Following | — | 1426 |

## Long Context

- GPT-5.1-Codex: —
- Hy3: 44.1 (#75)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena Longer Query | — | 1442 |

## Writing & Preference

- GPT-5.1-Codex: —
- Hy3: 62.2 (#81)

| Benchmark | GPT-5.1-Codex | Hy3 |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1402 |
| LMArena Multi-Turn | — | 1436 |

## FAQ

### Is GPT-5.1-Codex better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 38.6 on the Noometry Index.

### Which is cheaper, GPT-5.1-Codex or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

### Is GPT-5.1-Codex or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 41.9 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.1-Codex and Hy3 share?

1 benchmark has published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Hy3 has 19.