# Claude Opus 5.5 vs Hy3

> Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 44.2 on the Noometry Index. Hy3 costs 35× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-5-5-vs-hy3
- Last updated: 2026-10-11
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Claude Opus 5.5 scores higher in 8 categories and Hy3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 88.5% for Claude Opus 5.5 and 41.2% for Hy3.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 5.5 | Hy3 |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 68.6 | 44.2 |
| Rank | 3 | 79 |
| Context | 1M | 262K |
| Input $/M | $4 | $0.13 |
| Output $/M | $20 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 5.5: 71.9 (#3)
- Hy3: 46.8 (#63)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena WebDev | 1813 | 1508 |
| LMArena Coding | 1547 | 1464 |
| FrontierCode | 54.6% | — |
| CursorBench | 57.8% | — |
| FrontierSWE | 62.3% | — |
| SciCode | 66.9% | — |
| MirrorCode | 77.4% | — |
| ALE-Bench | 2,147 | — |

## Agentic & Tool Use

- Claude Opus 5.5: 45.3 (#15)
- Hy3: —

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| APEX-Agents | 73.5% | — |
| GDP.pdf | 30.6% | — |
| Vending-Bench 2 | 9,235 | — |

## Reasoning

- Claude Opus 5.5: 80.2 (#3)
- Hy3: 26.1 (#136)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 88.5% | 41.2% |
| LMArena Hard Prompts | 1535 | 1447 |
| ARC-AGI-2 | 93.3% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| EBR-Bench | 71.4% | — |
| Mystery Game Puzzles | 71% | — |
| DTBench | 98.9% | — |
| LMCA | 68.2% | — |
| Epoch Capabilities Index | 167.33 | — |

## Math

- Claude Opus 5.5: 91.8 (#3)
- Hy3: 40.1 (#93)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Math | 1506 | 1475 |
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| FrontierMath Erdős | 2.9% | — |

## Knowledge

- Claude Opus 5.5: 66.4 (#10)
- Hy3: 40.8 (#114)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Expert | 1547 | 1460 |
| GPQA Diamond | 90.6% | — |
| SimpleQA Verified | 72.2% | — |

## Multimodal

- Claude Opus 5.5: 57.8 (#1)
- Hy3: —

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 51.2% | — |
| Furniture Assembly | 83.3% | — |

## Multilingual

- Claude Opus 5.5: 59.1 (#2)
- Hy3: 53.5 (#65)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Non-English | 1507 | 1426 |
| LMArena Chinese | 1588 | 1493 |
| LMArena French | 1514 | 1461 |
| LMArena Russian | 1520 | 1432 |
| LMArena Spanish | 1507 | 1456 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |

## Instruction Following

- Claude Opus 5.5: 80.0 (#3)
- Hy3: 75.1 (#70)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1537 | 1426 |

## Long Context

- Claude Opus 5.5: 47.1 (#19)
- Hy3: 44.1 (#75)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1532 | 1442 |

## Writing & Preference

- Claude Opus 5.5: 78.2 (#3)
- Hy3: 62.2 (#81)

| Benchmark | Claude Opus 5.5 | Hy3 |
|---|---|---|
| LMArena Text | 1515 | 1439 |
| LMArena Creative Writing | 1533 | 1402 |
| LMArena Multi-Turn | 1499 | 1436 |
| EQ-Bench Creative Writing | 2050 | — |

## FAQ

### Is Claude Opus 5.5 better than Hy3?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 44.2 on the Noometry Index. Hy3 costs 35× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 5.5 or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Claude Opus 5.5 lists at $4 and $20.

### Is Claude Opus 5.5 or Hy3 better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 46.8 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 262K.

### How many benchmarks do Claude Opus 5.5 and Hy3 share?

16 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and Hy3 has 19.