DeepSeek V3.1 Terminus vs Hy3
Hy3 costs 3.1x less per output token than DeepSeek V3.1 Terminus ($0.33 vs $1.0142 per million). Updated October 21, 2026; 32 benchmarks have a result for both.
DeepSeek V3.1 Terminus or Hy3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V3.1 Terminus for work measured by SciCode or ALE-Bench, where it leads.
- Shared results
- 32
- DeepSeek V3.1 Terminus only
- 13
- Hy3 only
- 12
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
No call
Only DeepSeek V3.1 Terminus has a AA Intelligence Index result, 14.8.
Directional only
Agentic work
AA Agentic Index
No call
Only DeepSeek V3.1 Terminus has a AA Agentic Index result, 6.8.
Directional only
Web design
Design Arena: websites
Hy3
Hy3 leads, 1230 against 1187.
Same board, both measured
Long documents
Listed context window
Hy3
Hy3 takes 262K tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
DeepSeek V3.1 Terminus $0.0008, Hy3 $0.0002 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3.1 Terminus not benchmarked, Hy3 not benchmarked.
- Widest category
- Math, 11.9 points apart on average over 1 shared benchmark.
- Widest single gap
- Humanity's Last Exam (Artificial Analysis run): DeepSeek V3.1 Terminus 16.4% against Hy3 33.5%, 17.1 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V3.1 Terminus $1.0142 against Hy3 $0.33 per million output tokens, 3.1x apart.
- Context window
- DeepSeek V3.1 Terminus takes 164K tokens, Hy3 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V3.1 Terminus | Bars | Hy3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 1 | ||
| Knowledge | 2 | 2 | ||
| Web design | 1 | 6 | ||
| General | 2 | 10 | ||
| All shared boards | 5 | 27 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1507 | Only Hy3 measured |
| AA Coding Index | 43.5 | Not measured | Only DeepSeek V3.1 Terminus measured |
| LiveCodeBench (Artificial Analysis run) | 79.8% | Not measured | Only DeepSeek V3.1 Terminus measured |
| SciCode | 38.0% | 48.6% | Hy3 |
| Terminal-Bench Hard (Artificial Analysis run) | 31.8% | Not measured | Only DeepSeek V3.1 Terminus measured |
| ALE-Bench | 745.2 | 838.6 | Hy3 |
| LMArena Text: coding | 1425 | 1466 | Hy3 |
| LMArena Text: software and IT | 1426 | 1463 | Hy3 |
| LMArena WebDev: React | Not measured | 1511 | Only Hy3 measured |
| LMArena WebDev: HTML | Not measured | 1487 | Only Hy3 measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 14.8 | Not measured | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| AA Agentic Index | 6.8 | Not measured | Only DeepSeek V3.1 Terminus measured |
| τ²-Bench Telecom | 37.1% | Not measured | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 79.2% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 16.4% | 33.5% | Hy3 |
| LMArena Text: hard prompts | 1426 | 1447 | Hy3 |
| LMArena Text: expert | Not measured | 1461 | Only Hy3 measured |
| LMArena Text: hard prompts in English | 1432 | 1455 | Hy3 |
| Kagi LLM Benchmark | 57.4% | Not measured | Only DeepSeek V3.1 Terminus measured |
| Neither model has a result on the other 16 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| AA Math Index | 89.7 | Not measured | Only DeepSeek V3.1 Terminus measured |
| AIME 2025 (Artificial Analysis run) | 89.7% | Not measured | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: math | 1402 | 1473 | Hy3 |
| LMArena Text: mathematical work | Not measured | 1482 | Only Hy3 measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 85.1% | Not measured | Only DeepSeek V3.1 Terminus measured |
| LMArena Text: science | 1451 | 1457 | Hy3 |
| LMArena Text: medicine and healthcare | 1468 | 1452 | DeepSeek V3.1 Terminus |
| LMArena Text: legal and government | 1457 | 1422 | DeepSeek V3.1 Terminus |
| LMArena Text: business and finance | 1414 | 1424 | Hy3 |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1187 | 1230 | Hy3 |
| Design Arena: UI components | 1182 | 1207 | Hy3 |
| Design Arena: game dev | 1131 | 1208 | Hy3 |
| Design Arena: data viz | 1167 | 1163 | DeepSeek V3.1 Terminus |
| Design Arena: 3D | 1141 | 1233 | Hy3 |
| Design Arena: all code categories | 1175 | 1227 | Hy3 |
| Design Arena: SVG | 1065 | 1200 | Hy3 |
| Design Arena: ASCII art | Not measured | 1152 | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| IFBench | 57.0% | Not measured | Only DeepSeek V3.1 Terminus measured |
| Long context reasoning (AA-LCR) | 69.3% | 79.0% | Hy3 |
| DTBench | 81.3% | Not measured | Only DeepSeek V3.1 Terminus measured |
| LMCA | 28.6% | Not measured | Only DeepSeek V3.1 Terminus measured |
| LMArena Text | 1419 | 1438 | Hy3 |
| LMArena Text: instruction following | 1404 | 1426 | Hy3 |
| LMArena Text: creative writing | 1403 | 1403 | DeepSeek V3.1 Terminus |
| LMArena Text: English | 1429 | 1448 | Hy3 |
| LMArena Text: non-English | 1408 | 1426 | Hy3 |
| LMArena Text: Chinese | Not measured | 1485 | Only Hy3 measured |
| LMArena Text: German | Not measured | 1449 | Only Hy3 measured |
| LMArena Text: Japanese | Not measured | 1397 | Only Hy3 measured |
| LMArena Text: Korean | Not measured | 1396 | Only Hy3 measured |
| LMArena Text: French | Not measured | 1456 | Only Hy3 measured |
| LMArena Text: Spanish | Not measured | 1457 | Only Hy3 measured |
| LMArena Text: Russian | 1435 | 1432 | DeepSeek V3.1 Terminus |
| LMArena Text: Polish | 1427 | 1447 | Hy3 |
| LMArena Text: multi-turn | 1411 | 1436 | Hy3 |
| LMArena Text: longer queries | 1422 | 1442 | Hy3 |
| LMArena Text: writing and language | 1409 | 1414 | Hy3 |
| LMArena Text: entertainment and media | 1391 | 1400 | Hy3 |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3.1 Terminus | Hy3 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V3.1 Terminus | Tencent Hy3 |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Weights | Open weights | Open weights |
| Released | September 22, 2025 | July 6, 2026 |
| Context window | 164K | 262K |
| Input $/Mtok | $0.3063 | $0.0825 |
| Output $/Mtok | $1.0142 | $0.33 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3.1 Terminus better than Hy3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V3.1 Terminus for work measured by SciCode or ALE-Bench, where it leads.
Which is cheaper, DeepSeek V3.1 Terminus or Hy3?
DeepSeek V3.1 Terminus costs $0.3063 per million input tokens and $1.0142 per million output tokens; Hy3 costs $0.0825 and $0.33. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3.1 Terminus or Hy3?
Hy3, with 262K tokens against 164K.
How many benchmarks is the DeepSeek V3.1 Terminus vs Hy3 comparison based on?
32 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3.1 Terminus's coding index rests on 0 independent benchmarks and Hy3's on 1. Where only one model has a result, the page says so instead of naming a winner.