# Claude Haiku 4.5 vs Hy3

> Hy3 is the stronger model overall, scoring 44.2 to 39.5 on the Noometry Index.

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

## Summary

- They share 19 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Hy3 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 26.1 to 15.1.
- The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Hy3 accepts more context: 262K tokens versus 200K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 39.5 | 44.2 |
| Rank | 165 | 79 |
| Context | 200K | 262K |
| Input $/M | $1 | $0.0825 |
| Output $/M | $5 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Hy3: 46.8 (#63)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1330 | 1508 |
| LMArena Coding | 1453 | 1464 |
| SWE-bench Verified (bash only) | 66.6% | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Hy3: —

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#320)
- Hy3: 26.1 (#136)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 14.3% | 41.2% |
| LMArena Hard Prompts | 1420 | 1447 |
| ARC-AGI-2 | 4% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 44.9 (#78)
- Hy3: 40.1 (#93)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Math | 1396 | 1475 |
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.7 (#153)
- Hy3: 40.8 (#114)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1442 | 1460 |
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Hy3: —

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Hy3: 53.5 (#65)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1377 | 1426 |
| LMArena Chinese | 1417 | 1493 |
| LMArena French | 1408 | 1461 |
| LMArena German | 1375 | 1439 |
| LMArena Japanese | 1339 | 1392 |
| LMArena Korean | 1347 | 1395 |
| LMArena Russian | 1381 | 1432 |
| LMArena Spanish | 1420 | 1456 |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Hy3: 75.1 (#70)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1414 | 1426 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Hy3: 44.1 (#75)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1427 | 1442 |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Hy3: 62.2 (#81)

| Benchmark | Claude Haiku 4.5 | Hy3 |
|---|---|---|
| LMArena Text | 1396 | 1439 |
| LMArena Creative Writing | 1372 | 1402 |
| LMArena Multi-Turn | 1409 | 1436 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Hy3?

Hy3 is the stronger model overall, scoring 44.2 to 39.5 on the Noometry Index.

### Which is cheaper, Claude Haiku 4.5 or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

### Is Claude Haiku 4.5 or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 44.0 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

### How many benchmarks do Claude Haiku 4.5 and Hy3 share?

19 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Hy3 has 19.