# Claude Opus 4.8 vs Hy3

> Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 44.2 on the Noometry Index. Hy3 costs 69× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-opus-4-8-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude Opus 4.8 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 4.8 leads 64.7 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 91.1% for Claude Opus 4.8 and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
- Claude Opus 4.8 accepts more context: 1M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Opus 4.8 | Hy3 |
|---|---|---|
| Provider | Anthropic | Tencent |
| Noometry Index | 60.7 | 44.2 |
| Rank | 13 | 79 |
| Context | 1M | 262K |
| Input $/M | $5 | $0.0825 |
| Output $/M | $25 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Claude Opus 4.8: 59.9 (#12)
- Hy3: 46.8 (#63)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena WebDev | 1556 | 1508 |
| LMArena Coding | 1490 | 1464 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| WeirdML | 82.9% | — |
| ALE-Bench | 1,564 | — |

## Agentic & Tool Use

- Claude Opus 4.8: 47.6 (#11)
- Hy3: —

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |

## Reasoning

- Claude Opus 4.8: 64.7 (#16)
- Hy3: 26.1 (#136)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| NYT Connections (extended) | 91.1% | 41.2% |
| LMArena Hard Prompts | 1482 | 1447 |
| ARC-AGI-2 | 72.1% | — |
| SimpleBench | 64.8% | — |
| Kagi LLM Benchmark | 88.8% | — |
| ARC-AGI-1 | 92.5% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| Mystery Game Puzzles | 36% | — |
| DTBench | 94.9% | — |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| Epoch Capabilities Index | 158.21 | — |
| ForecastBench | 59.9 | — |

## Math

- Claude Opus 4.8: 78.4 (#13)
- Hy3: 40.1 (#93)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Math | 1487 | 1475 |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 69% | — |
| FrontierMath (Feb 2025 set) | 47.2% | — |
| FrontierMath Tier 4 (v1) | 31.3% | — |

## Knowledge

- Claude Opus 4.8: 61.3 (#29)
- Hy3: 40.8 (#114)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Expert | 1502 | 1460 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 53% | — |

## Multimodal

- Claude Opus 4.8: 42.9 (#26)
- Hy3: —

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Vision | 1294 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |

## Multilingual

- Claude Opus 4.8: 55.2 (#33)
- Hy3: 53.5 (#65)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Non-English | 1450 | 1426 |
| LMArena Chinese | 1507 | 1493 |
| LMArena French | 1481 | 1461 |
| LMArena German | 1472 | 1439 |
| LMArena Japanese | 1440 | 1392 |
| LMArena Korean | 1432 | 1395 |
| LMArena Russian | 1474 | 1432 |
| LMArena Spanish | 1466 | 1456 |

## Instruction Following

- Claude Opus 4.8: 77.4 (#24)
- Hy3: 75.1 (#70)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1476 | 1426 |

## Long Context

- Claude Opus 4.8: 45.4 (#35)
- Hy3: 44.1 (#75)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1483 | 1442 |

## Writing & Preference

- Claude Opus 4.8: 72.0 (#16)
- Hy3: 62.2 (#81)

| Benchmark | Claude Opus 4.8 | Hy3 |
|---|---|---|
| LMArena Text | 1461 | 1439 |
| LMArena Creative Writing | 1454 | 1402 |
| LMArena Multi-Turn | 1476 | 1436 |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |

## FAQ

### Is Claude Opus 4.8 better than Hy3?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 44.2 on the Noometry Index. Hy3 costs 69× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

### Which is cheaper, Claude Opus 4.8 or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Claude Opus 4.8 lists at $5 and $25.

### Is Claude Opus 4.8 or Hy3 better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 46.8 in the Noometry coding category.

### Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 262K.

### How many benchmarks do Claude Opus 4.8 and Hy3 share?

19 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Hy3 has 19.