Model comparison
DeepSeek-V3.1 vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 2.6× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
DeepSeek
TencentSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 38.9.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.75 / $2.25 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-V3.1 | Hy4 preview | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 42.8 | 45.3 |
| Released | 2025-08-21 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 8K | 64K |
| Input $ / M tokens | $0.25 | $0.75 |
| Output $ / M tokens | $0.95 | $2.25 |
| Results tracked | 27 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
DeepSeek-V3.1: 40.3 (#144), Hy4 preview: 51.6 (#38)
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| WeirdML | 38.4% | — |
| LMArena Coding | 1417 | — |
Reasoning Hy4 preview leads
DeepSeek-V3.1: 27.9 (#110), Hy4 preview: 31.9 (#79)
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 68.2% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Hy4 preview leads
DeepSeek-V3.1: 38.9 (#122), Hy4 preview: 55.7 (#42)
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| LMArena Math | 1420 | — |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), Hy4 preview: —
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual Not comparable
DeepSeek-V3.1: 51.6 (#106), Hy4 preview: —
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
DeepSeek-V3.1: 73.9 (#110), Hy4 preview: —
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
DeepSeek-V3.1: 36.3 (#232), Hy4 preview: —
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
DeepSeek-V3.1: 60.3 (#98), Hy4 preview: —
| Benchmark | DeepSeek-V3.1 | Hy4 preview |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 2.6× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 or Hy4 preview?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Hy4 preview lists at $0.75 and $2.25.
Is DeepSeek-V3.1 or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Hy4 preview share?
0 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Hy4 preview has 3.