# Claude 3 Haiku vs Hy3

> Hy3 is the stronger model overall, scoring 44.2 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 29.7.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Hy3 |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 25.9 | 44.2 |
| Rank | 340 | 79 |
| Context | — | 262K |
| Input $/M | — | $0.0825 |
| Output $/M | — | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Hy3: 46.8 (#63)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Coding | 1199 | 1464 |
| LMArena WebDev | — | 1508 |
| WeirdML | 9.8% | — |
| BigCodeBench Instruct | 39.4% | — |
| BigCodeBench Complete | 50.1% | — |
| CadEval | 12% | — |
| HumanEval+ | 68.9% | — |
| MBPP+ | 68.8% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Hy3: 26.1 (#136)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1447 |
| Kagi LLM Benchmark | 34.2% | — |
| NYT Connections (extended) | — | 41.2% |
| DTBench | 50.1% | — |
| LMCA | 8.8% | — |
| Epoch Capabilities Index | 118.35 | — |
| ForecastBench | 53.2 | — |
| WinoGrande | 74.2% | — |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Hy3: 40.1 (#93)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Math | 1188 | 1475 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| MATH Level 5 | 14.9% | — |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Hy3: 40.8 (#114)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Expert | 1148 | 1460 |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| MMLU | 73.8% | — |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Hy3: —

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Hy3: 53.5 (#65)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Non-English | 1178 | 1426 |
| LMArena Chinese | 1155 | 1493 |
| LMArena French | 1195 | 1461 |
| LMArena German | 1174 | 1439 |
| LMArena Japanese | 1102 | 1392 |
| LMArena Korean | 1109 | 1395 |
| LMArena Russian | 1204 | 1432 |
| LMArena Spanish | 1166 | 1456 |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Hy3: 75.1 (#70)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1173 | 1426 |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Hy3: 44.1 (#75)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Longer Query | 1190 | 1442 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Hy3: 62.2 (#81)

| Benchmark | Claude 3 Haiku | Hy3 |
|---|---|---|
| LMArena Text | 1195 | 1439 |
| LMArena Creative Writing | 1157 | 1402 |
| LMArena Multi-Turn | 1190 | 1436 |
| EQ-Bench Creative Writing | 717 | — |

## FAQ

### Is Claude 3 Haiku better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 26.4 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Hy3 share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Hy3 has 19.