Model comparison
DeepSeek-R1 vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 42.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
TencentSummary
- They share 17 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 26.1 to 18.6.
- 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.
Side by side
| DeepSeek-R1 | Hy3 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 42.3 | 44.2 |
| Released | 2025-01-20 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 128K |
| Input $ / M tokens | $0.50 | $0.13 |
| Output $ / M tokens | $2.15 | $0.53 |
| Results tracked | 52 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-R1: 46.3 (#68), Hy3: 46.8 (#63)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Coding | 1427 | 1464 |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1508 |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Hy3: —
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Hy3 leads
DeepSeek-R1: 18.6 (#278), Hy3: 26.1 (#136)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1447 |
| 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 | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Hy3: 40.1 (#93)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Math | 1400 | 1475 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Hy3: 40.8 (#114)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Expert | 1394 | 1460 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual Hy3 leads
DeepSeek-R1: 52.4 (#85), Hy3: 53.5 (#65)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Non-English | 1412 | 1426 |
| LMArena Chinese | 1442 | 1493 |
| LMArena French | 1417 | 1461 |
| LMArena German | 1404 | 1439 |
| LMArena Japanese | 1391 | 1392 |
| LMArena Korean | 1360 | 1395 |
| LMArena Russian | 1423 | 1432 |
| LMArena Spanish | 1411 | 1456 |
Instruction Following Hy3 leads
DeepSeek-R1: 72.0 (#143), Hy3: 75.1 (#70)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1382 | 1426 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Hy3: 44.1 (#75)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Longer Query | 1391 | 1442 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Too close to call
DeepSeek-R1: 61.4 (#88), Hy3: 62.2 (#81)
| Benchmark | DeepSeek-R1 | Hy3 |
|---|---|---|
| LMArena Text | 1428 | 1439 |
| LMArena Creative Writing | 1405 | 1402 |
| LMArena Multi-Turn | 1405 | 1436 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 42.3 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 (46.3 vs 46.8); 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?
17 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Hy3 has 19.