# DeepSeek-R1 vs Hy3

> Hy3 is the stronger model overall, scoring 43.6 to 42.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-r1-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek-R1 scores higher in 3 categories and Hy3 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Hy3 leads 25.0 to 18.7.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Hy3 accepts more context: 262K tokens versus 164K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-R1 | Hy3 |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 42.0 | 43.6 |
| Rank | 110 | 79 |
| Context | 164K | 262K |
| Input $/M | $0.50 | $0.13 |
| Output $/M | $2.15 | $0.53 |
| Weights | Proprietary | Open |

## Coding

- DeepSeek-R1: 45.9 (#63)
- Hy3: 46.6 (#60)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Coding | 1427 | 1465 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1509 |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |

## Agentic & Tool Use

- DeepSeek-R1: 30.4 (#68)
- Hy3: —

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |

## Reasoning

- DeepSeek-R1: 18.7 (#253)
- Hy3: 25.0 (#134)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1415 | 1449 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.3 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |

## Math

- DeepSeek-R1: 42.0 (#70)
- Hy3: 37.4 (#98)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Math | 1401 | 1475 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |

## Knowledge

- DeepSeek-R1: 44.3 (#81)
- Hy3: 40.2 (#108)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Expert | 1394 | 1461 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |

## Multilingual

- DeepSeek-R1: 52.6 (#80)
- Hy3: 53.7 (#60)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Non-English | 1412 | 1427 |
| LMArena Chinese | 1443 | 1496 |
| LMArena French | 1415 | 1461 |
| LMArena Korean | 1359 | 1390 |
| LMArena Russian | 1423 | 1435 |
| LMArena Spanish | 1410 | 1448 |
| LMArena German | 1405 | — |
| LMArena Japanese | 1394 | — |

## Instruction Following

- DeepSeek-R1: 72.2 (#138)
- Hy3: 75.3 (#68)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1425 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |

## Long Context

- DeepSeek-R1: 45.4 (#36)
- Hy3: 44.1 (#70)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1391 | 1443 |
| Fiction.LiveBench | 75% | — |

## Writing & Preference

- DeepSeek-R1: 61.5 (#84)
- Hy3: 62.5 (#75)

| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Text | 1428 | 1442 |
| LMArena Creative Writing | 1406 | 1399 |
| LMArena Multi-Turn | 1404 | 1436 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |

## FAQ

### Is DeepSeek-R1 better than Hy3?

Hy3 is the stronger model overall, scoring 43.6 to 42.0 on the Noometry Index.

### Which is cheaper, DeepSeek-R1 or Hy3?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.

### Is DeepSeek-R1 or Hy3 better for coding?

They score almost the same on coding (45.9 vs 46.6); test both on your own repository before choosing.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 164K.

### How many benchmarks do DeepSeek-R1 and Hy3 share?

15 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Hy3 has 17.