Hermes 3 70B Instruct vs Solar Pro 4
Solar Pro 4 leads Hermes 3 70B Instruct on the Artificial Analysis Intelligence Index, 28.2 to 6.7, at about the same output price ($0.60 vs $0.70 per million). Updated October 23, 2026; 3 benchmarks have a result for both.
Hermes 3 70B Instruct or Solar Pro 4: 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 AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 3
- Hermes 3 70B Instruct only
- 2
- Solar Pro 4 only
- 42
- Like-for-like categories
- 2 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
Solar Pro 4
Solar Pro 4 leads, 28.2 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only Solar Pro 4 has a Design Arena: websites result, 1176.
Directional only
Long documents
Listed context window
Solar Pro 4
Solar Pro 4 takes 524K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Pro 4
Hermes 3 70B Instruct $0.0010, Solar Pro 4 $0.0004 per turn.
List prices
At a glance
- Coding index
- Hermes 3 70B Instruct not benchmarked, Solar Pro 4 not benchmarked.
- Widest category
- Reasoning, 37.4 points apart on average over 2 shared benchmarks.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): Hermes 3 70B Instruct 40.1% against Solar Pro 4 89.1%, 49.0 points apart on a 0 to 100 scale.
- Output price
- Hermes 3 70B Instruct $0.70 against Solar Pro 4 $0.60 per million output tokens, 1.2x apart.
- Context window
- Hermes 3 70B Instruct takes 131K tokens, Solar Pro 4 524K.
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 | Solar Pro 4 | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| All shared boards | 0 | 3 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index9 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1370 | Only Solar Pro 4 measured |
| AA Coding Index | Not measured | 52.7 | Only Solar Pro 4 measured |
| LiveCodeBench (Artificial Analysis run) | 18.8% | Not measured | Only Hermes 3 70B Instruct measured |
| SciCode | Not measured | 48.0% | Only Solar Pro 4 measured |
| ALE-Bench | Not measured | 179.3 | Only Solar Pro 4 measured |
| LMArena Text: coding | Not measured | 1437 | Only Solar Pro 4 measured |
| LMArena Text: software and IT | Not measured | 1431 | Only Solar Pro 4 measured |
| LMArena WebDev: React | Not measured | 1363 | Only Solar Pro 4 measured |
| LMArena WebDev: HTML | Not measured | 1371 | Only Solar Pro 4 measured |
| Neither model has a result on the other 34 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 28.2 | Solar Pro 4 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1105 | Only Solar Pro 4 measured |
| Neither model has a result on the other 41 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 40.1% | 89.1% | Solar Pro 4 |
| Humanity's Last Exam (Artificial Analysis run) | 4.0% | 29.8% | Solar Pro 4 |
| LMArena Text: hard prompts | Not measured | 1400 | Only Solar Pro 4 measured |
| LMArena Text: expert | Not measured | 1428 | Only Solar Pro 4 measured |
| LMArena Text: hard prompts in English | Not measured | 1428 | Only Solar Pro 4 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 | Solar Pro 4 | Leader |
|---|---|---|---|
| LMArena Text: math | Not measured | 1417 | Only Solar Pro 4 measured |
| LMArena Text: mathematical work | Not measured | 1423 | Only Solar Pro 4 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 | Solar Pro 4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 57.1% | Not measured | Only Hermes 3 70B Instruct measured |
| LMArena Text: science | Not measured | 1403 | Only Solar Pro 4 measured |
| LMArena Text: medicine and healthcare | Not measured | 1374 | Only Solar Pro 4 measured |
| LMArena Text: legal and government | Not measured | 1384 | Only Solar Pro 4 measured |
| LMArena Text: business and finance | Not measured | 1381 | Only Solar Pro 4 measured |
| Neither model has a result on the other 15 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1176 | Only Solar Pro 4 measured |
| Design Arena: UI components | Not measured | 1147 | Only Solar Pro 4 measured |
| Design Arena: game dev | Not measured | 1169 | Only Solar Pro 4 measured |
| Design Arena: data viz | Not measured | 1178 | Only Solar Pro 4 measured |
| Design Arena: 3D | Not measured | 1179 | Only Solar Pro 4 measured |
| Design Arena: all code categories | Not measured | 1182 | Only Solar Pro 4 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index18 boards, none shared
| Benchmark | Hermes 3 70B Instruct | Solar Pro 4 | Leader |
|---|---|---|---|
| Long context reasoning (AA-LCR) | Not measured | 70.7% | Only Solar Pro 4 measured |
| LMArena Text | Not measured | 1388 | Only Solar Pro 4 measured |
| LMArena Text: instruction following | Not measured | 1374 | Only Solar Pro 4 measured |
| LMArena Text: creative writing | Not measured | 1318 | Only Solar Pro 4 measured |
| LMArena Text: English | Not measured | 1415 | Only Solar Pro 4 measured |
| LMArena Text: non-English | Not measured | 1363 | Only Solar Pro 4 measured |
| LMArena Text: Chinese | Not measured | 1423 | Only Solar Pro 4 measured |
| LMArena Text: German | Not measured | 1357 | Only Solar Pro 4 measured |
| LMArena Text: Japanese | Not measured | 1320 | Only Solar Pro 4 measured |
| LMArena Text: Korean | Not measured | 1391 | Only Solar Pro 4 measured |
| LMArena Text: French | Not measured | 1403 | Only Solar Pro 4 measured |
| LMArena Text: Spanish | Not measured | 1413 | Only Solar Pro 4 measured |
| LMArena Text: Russian | Not measured | 1354 | Only Solar Pro 4 measured |
| LMArena Text: Polish | Not measured | 1307 | Only Solar Pro 4 measured |
| LMArena Text: multi-turn | Not measured | 1387 | Only Solar Pro 4 measured |
| LMArena Text: longer queries | Not measured | 1382 | Only Solar Pro 4 measured |
| LMArena Text: writing and language | Not measured | 1344 | Only Solar Pro 4 measured |
| LMArena Text: entertainment and media | Not measured | 1333 | Only Solar Pro 4 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 | Solar Pro 4 | 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
Solar Pro 4 costs less
Repository review
50K input + 3K output tokens
Solar Pro 4 costs less
Agent loop
200K input + 10K output tokens
Solar Pro 4 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 | Upstage Solar Pro 4 |
|---|---|---|
| Maker | Nous Research | Upstage |
| Weights | Open weights | No public weights listed |
| Released | August 18, 2024 | August 10, 2026 |
| Context window | 131K | 524K |
| Input $/Mtok | $0.70 | $0.15 |
| Output $/Mtok | $0.70 | $0.60 |
| 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 Solar Pro 4 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 AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, Hermes 3 70B Instruct or Solar Pro 4?
Hermes 3 70B Instruct costs $0.70 per million input tokens and $0.70 per million output tokens; Solar Pro 4 costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, Hermes 3 70B Instruct or Solar Pro 4?
Solar Pro 4, with 524K tokens against 131K.
How many benchmarks is the Hermes 3 70B Instruct vs Solar Pro 4 comparison based on?
3 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 Solar Pro 4's on 1. Where only one model has a result, the page says so instead of naming a winner.