Hermes 3 70B Instruct vs Hy3
Hy3 costs 1.3x less per output token than Hermes 3 70B Instruct ($0.528 vs $0.70 per million). Updated October 23, 2026; 2 benchmarks have a result for both.
Hermes 3 70B Instruct or Hy3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Hermes 3 70B Instruct for work measured by GPQA Diamond (Artificial Analysis run) or Humanity's Last Exam (Artificial Analysis run), where it leads.
- Shared results
- 2
- Hermes 3 70B Instruct only
- 3
- Hy3 only
- 42
- Like-for-like categories
- 1 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 Hermes 3 70B Instruct has a AA Intelligence Index result, 6.7.
Directional only
Web design
Design Arena: websites
No call
Only Hy3 has a Design Arena: websites result, 1230.
Directional only
Long documents
Listed context window
Hy3
Hy3 takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
Hermes 3 70B Instruct $0.0010, Hy3 $0.0004 per turn.
List prices
At a glance
- Coding index
- Hermes 3 70B Instruct not benchmarked, Hy3 not benchmarked.
- Widest category
- Reasoning, 39.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): Hermes 3 70B Instruct 40.1% against Hy3 89.7%, 49.6 points apart on a 0 to 100 scale.
- Output price
- Hermes 3 70B Instruct $0.70 against Hy3 $0.528 per million output tokens, 1.3x apart.
- Context window
- Hermes 3 70B Instruct takes 131K 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 | Hermes 3 70B Instruct | Bars | Hy3 | Ties |
|---|---|---|---|---|
| Reasoning | 0 | 2 | ||
| All shared boards | 0 | 2 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1506 | Only Hy3 measured |
| LiveCodeBench (Artificial Analysis run) | 18.8% | Not measured | Only Hermes 3 70B Instruct measured |
| SciCode | Not measured | 48.6% | Only Hy3 measured |
| ALE-Bench | Not measured | 838.6 | Only Hy3 measured |
| LMArena Text: coding | Not measured | 1466 | Only Hy3 measured |
| LMArena Text: software and IT | Not measured | 1463 | Only Hy3 measured |
| LMArena WebDev: React | Not measured | 1509 | Only Hy3 measured |
| LMArena WebDev: HTML | Not measured | 1486 | Only Hy3 measured |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | Not measured | Only Hermes 3 70B Instruct measured |
| Neither model has a result on the other 1 board here | |||
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| Neither model has a result on 42 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 40.1% | 89.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 4.0% | 33.5% | Hy3 |
| LMArena Text: hard prompts | Not measured | 1448 | Only Hy3 measured |
| LMArena Text: expert | Not measured | 1461 | Only Hy3 measured |
| LMArena Text: hard prompts in English | Not measured | 1454 | Only Hy3 measured |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| LMArena Text: math | Not measured | 1476 | Only Hy3 measured |
| LMArena Text: mathematical work | Not measured | 1483 | Only Hy3 measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 57.1% | Not measured | Only Hermes 3 70B Instruct measured |
| LMArena Text: science | Not measured | 1457 | Only Hy3 measured |
| LMArena Text: medicine and healthcare | Not measured | 1449 | Only Hy3 measured |
| LMArena Text: legal and government | Not measured | 1422 | Only Hy3 measured |
| LMArena Text: business and finance | Not measured | 1424 | Only Hy3 measured |
| Neither model has a result on the other 15 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1230 | Only Hy3 measured |
| Design Arena: UI components | Not measured | 1204 | Only Hy3 measured |
| Design Arena: game dev | Not measured | 1208 | Only Hy3 measured |
| Design Arena: data viz | Not measured | 1165 | Only Hy3 measured |
| Design Arena: 3D | Not measured | 1233 | Only Hy3 measured |
| Design Arena: all code categories | Not measured | 1227 | Only Hy3 measured |
| Design Arena: SVG | Not measured | 1201 | Only Hy3 measured |
| Design Arena: ASCII art | Not measured | 1152 | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Hy3 | Leader |
|---|---|---|---|
| Long context reasoning (AA-LCR) | Not measured | 79.0% | Only Hy3 measured |
| LMArena Text | Not measured | 1438 | Only Hy3 measured |
| LMArena Text: instruction following | Not measured | 1427 | Only Hy3 measured |
| LMArena Text: creative writing | Not measured | 1405 | Only Hy3 measured |
| LMArena Text: English | Not measured | 1447 | Only Hy3 measured |
| LMArena Text: non-English | Not measured | 1427 | Only Hy3 measured |
| LMArena Text: Chinese | Not measured | 1483 | Only Hy3 measured |
| LMArena Text: German | Not measured | 1444 | Only Hy3 measured |
| LMArena Text: Japanese | Not measured | 1393 | Only Hy3 measured |
| LMArena Text: Korean | Not measured | 1396 | Only Hy3 measured |
| LMArena Text: French | Not measured | 1450 | Only Hy3 measured |
| LMArena Text: Spanish | Not measured | 1456 | Only Hy3 measured |
| LMArena Text: Russian | Not measured | 1436 | Only Hy3 measured |
| LMArena Text: Polish | Not measured | 1446 | Only Hy3 measured |
| LMArena Text: multi-turn | Not measured | 1437 | Only Hy3 measured |
| LMArena Text: longer queries | Not measured | 1442 | Only Hy3 measured |
| LMArena Text: writing and language | Not measured | 1415 | Only Hy3 measured |
| LMArena Text: entertainment and media | Not measured | 1401 | Only Hy3 measured |
| Neither model has a result on the other 30 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hermes 3 70B Instruct | 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 | Nous Hermes 3 70B Instruct | Tencent Hy3 |
|---|---|---|
| Maker | Nous Research | Tencent |
| Weights | Open weights | Open weights |
| Released | August 18, 2024 | July 6, 2026 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.70 | $0.132 |
| Output $/Mtok | $0.70 | $0.528 |
| 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 Hermes 3 70B Instruct better than Hy3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Hermes 3 70B Instruct for work measured by GPQA Diamond (Artificial Analysis run) or Humanity's Last Exam (Artificial Analysis run), where it leads.
Which is cheaper, Hermes 3 70B Instruct or Hy3?
Hermes 3 70B Instruct costs $0.70 per million input tokens and $0.70 per million output tokens; Hy3 costs $0.132 and $0.528. Cost per solved task is known for neither of them.
Which has the bigger context window, Hermes 3 70B Instruct or Hy3?
Hy3, with 262K tokens against 131K.
How many benchmarks is the Hermes 3 70B Instruct vs Hy3 comparison based on?
2 benchmarks have a result for both models as of October 23, 2026. Hermes 3 70B Instruct'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.