# Hy3 vs Llama 3.1-70B

> Hy3 is the stronger model overall, scoring 43.6 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy3-vs-llama-3-1-70b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Hy3 scores higher in 8 categories and Llama 3.1-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 35.6.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
- Hy3 accepts more context: 262K tokens versus 128K.

## Snapshot

| | Hy3 | Llama 3.1-70B |
|---|---|---|
| Provider | Tencent | Meta |
| Noometry Index | 43.6 | 29.4 |
| Rank | 79 | 299 |
| Context | 262K | 128K |
| Input $/M | $0.13 | $0.40 |
| Output $/M | $0.53 | $0.40 |
| Weights | Open | Open |

## Coding

- Hy3: 46.6 (#60)
- Llama 3.1-70B: 29.8 (#292)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Coding | 1465 | 1260 |
| LMArena WebDev | 1509 | — |
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| BigCodeBench Complete | — | 54.8% |

## Agentic & Tool Use

- Hy3: —
- Llama 3.1-70B: 24.9 (#104)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |

## Reasoning

- Hy3: 25.0 (#134)
- Llama 3.1-70B: 20.8 (#215)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1241 |
| NYT Connections (extended) | 41.2% | — |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| Epoch Capabilities Index | — | 125.91 |

## Math

- Hy3: 37.4 (#98)
- Llama 3.1-70B: 12.7 (#298)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Math | 1475 | 1252 |
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| MATH Level 5 | — | 36.7% |

## Knowledge

- Hy3: 40.2 (#108)
- Llama 3.1-70B: 24.1 (#264)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Expert | 1461 | 1209 |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| MMLU | — | 80.1% |

## Multilingual

- Hy3: 53.7 (#60)
- Llama 3.1-70B: 38.9 (#220)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1427 | 1219 |
| LMArena Chinese | 1496 | 1215 |
| LMArena French | 1461 | 1260 |
| LMArena Korean | 1390 | 1140 |
| LMArena Russian | 1435 | 1234 |
| LMArena Spanish | 1448 | 1253 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |

## Instruction Following

- Hy3: 75.3 (#68)
- Llama 3.1-70B: 65.5 (#218)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1425 | 1231 |
| IFEval | — | 82.1% |

## Long Context

- Hy3: 44.1 (#70)
- Llama 3.1-70B: 37.6 (#208)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | 1443 | 1241 |

## Writing & Preference

- Hy3: 62.5 (#75)
- Llama 3.1-70B: 35.6 (#262)

| Benchmark | Hy3 | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1442 | 1261 |
| LMArena Creative Writing | 1399 | 1232 |
| LMArena Multi-Turn | 1436 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |

## FAQ

### Is Hy3 better than Llama 3.1-70B?

Hy3 is the stronger model overall, scoring 43.6 to 29.4 on the Noometry Index.

### Which is cheaper, Hy3 or Llama 3.1-70B?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.

### Is Hy3 or Llama 3.1-70B better for coding?

Hy3 scores higher on coding benchmarks: 46.6 versus 29.8 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 128K.

### How many benchmarks do Hy3 and Llama 3.1-70B share?

15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Llama 3.1-70B has 35.