Model comparison
DeepSeek-V3.1-Terminus vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 44.6 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus 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 54.5 to 35.7.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | Hy4 preview | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 42.6 | 44.6 |
| Released | 2025-09-22 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 66K | 64K |
| Input $ / M tokens | $0.30 | $0.83 |
| Output $ / M tokens | $1 | $2.50 |
| Results tracked | 16 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Hy4 preview: 51.4 (#36)
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1633 |
| SciCode | 40.6% | — |
| LMArena Coding | 1426 | — |
| ALE-Bench | 745.17 | — |
Reasoning Hy4 preview leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Hy4 preview: 30.6 (#75)
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 68.2% |
| CritPt | 1.7% | — |
| LMArena Hard Prompts | 1427 | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Hy4 preview leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Hy4 preview: 54.5 (#37)
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| LMArena Math | 1402 | — |
Multilingual Not comparable
DeepSeek-V3.1-Terminus: 52.3 (#87), Hy4 preview: —
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1434 | — |
Instruction Following Not comparable
DeepSeek-V3.1-Terminus: 74.4 (#96), Hy4 preview: —
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1406 | — |
Long Context Not comparable
DeepSeek-V3.1-Terminus: 43.5 (#88), Hy4 preview: —
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1426 | — |
Writing & Preference Not comparable
DeepSeek-V3.1-Terminus: 61.3 (#87), Hy4 preview: —
| Benchmark | DeepSeek-V3.1-Terminus | Hy4 preview |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1404 | — |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus 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-Terminus or Hy4 preview?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is DeepSeek-V3.1-Terminus or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 41.5 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-Terminus and Hy4 preview share?
0 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Hy4 preview has 3.