# GPT-5.4 mini vs Hy3

> GPT-5.4 mini and Hy3 score almost the same on the Noometry Index (45.0 vs 44.2), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GPT-5.4 mini scores higher in 4 categories and Hy3 in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 40.8.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Hy3 |
|---|---|---|
| Provider | OpenAI | Tencent |
| Noometry Index | 45.0 | 44.2 |
| Rank | 76 | 79 |
| Context | 400K | 262K |
| Input $/M | $0.75 | $0.0825 |
| Output $/M | $4.50 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Hy3: 46.8 (#63)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena WebDev | 1397 | 1508 |
| LMArena Coding | 1438 | 1464 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Hy3: —

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Hy3: 26.1 (#136)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| NYT Connections (extended) | 61.8% | 41.2% |
| LMArena Hard Prompts | 1424 | 1447 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Hy3: 40.1 (#93)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Math | 1419 | 1475 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Hy3: 40.8 (#114)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Expert | 1435 | 1460 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Hy3: —

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Hy3: 53.5 (#65)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Non-English | 1405 | 1426 |
| LMArena Chinese | 1446 | 1493 |
| LMArena French | 1440 | 1461 |
| LMArena German | 1409 | 1439 |
| LMArena Japanese | 1374 | 1392 |
| LMArena Korean | 1368 | 1395 |
| LMArena Russian | 1417 | 1432 |
| LMArena Spanish | 1405 | 1456 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Hy3: 75.1 (#70)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1426 |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Hy3: 44.1 (#75)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Longer Query | 1407 | 1442 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Hy3: 62.2 (#81)

| Benchmark | GPT-5.4 mini | Hy3 |
|---|---|---|
| LMArena Text | 1412 | 1439 |
| LMArena Creative Writing | 1370 | 1402 |
| LMArena Multi-Turn | 1429 | 1436 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Hy3?

GPT-5.4 mini and Hy3 score almost the same on the Noometry Index (45.0 vs 44.2), so choose on price, context window or the category you care about most.

### Which is cheaper, GPT-5.4 mini or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is GPT-5.4 mini or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 45.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.4 mini and Hy3 share?

19 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Hy3 has 19.