Nemotron 3 Ultra vs Solar Pro 4
Solar Pro 4 leads Nemotron 3 Ultra on the Artificial Analysis Intelligence Index, 28.2 to 22.9, and Solar Pro 4 costs 4.0x less per output token ($0.60 vs $2.40 per million). Updated October 22, 2026; 39 benchmarks have a result for both.
Nemotron 3 Ultra or Solar Pro 4: which to pick
Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Solar Pro 4 has none, so the two cannot be ranked on coding.
Pick Solar Pro 4 for output tokens 4.0x cheaper ($0.60 vs $2.40 per million) and a larger context window (524K against 262K tokens).
- Shared results
- 39
- Nemotron 3 Ultra only
- 32
- Solar Pro 4 only
- 6
- Like-for-like categories
- 7 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
Only Nemotron 3 Ultra has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Solar Pro 4
Solar Pro 4 leads, 28.2 against 22.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Nemotron 3 Ultra has a AA Agentic Index result, 20.1.
Directional only
Reasoning
GPQA Diamond
No call
Only Nemotron 3 Ultra has a GPQA Diamond result, 86.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Nemotron 3 Ultra has a MMLU Pro result, 85.8%.
Directional only
Web design
Design Arena: websites
Solar Pro 4
Solar Pro 4 leads, 1176 against 1145.
Same board, both measured
Long documents
Listed context window
Solar Pro 4
Solar Pro 4 takes 524K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Pro 4
Nemotron 3 Ultra $0.0018, Solar Pro 4 $0.0004 per turn.
List prices
At a glance
- Coding index
- Nemotron 3 Ultra 30.0 from 3 benchmarks, Solar Pro 4 not benchmarked.
- Widest category
- Knowledge, 11.0 points apart on average over 4 shared benchmarks.
- Widest single gap
- LMArena Text: German: Nemotron 3 Ultra 1472 against Solar Pro 4 1358, 19.0 points apart on a 0 to 100 scale.
- Output price
- Nemotron 3 Ultra $2.40 against Solar Pro 4 $0.60 per million output tokens, 4.0x apart.
- Context window
- Nemotron 3 Ultra takes 262K 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 | Nemotron 3 Ultra | Bars | Solar Pro 4 | Ties |
|---|---|---|---|---|
| Coding | 2 | 2 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 3 | 2 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| Web design | 0 | 6 | ||
| General | 17 | 0 | ||
| All shared boards | 28 | 11 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index22
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1371 | Only Solar Pro 4 measured |
| AA Coding Index | 49.3 | 52.7 | Solar Pro 4 |
| LiveCodeBench (Vals AI) | 86.0% | Not measured | Only Nemotron 3 Ultra measured |
| SWE-bench Verified (Vals AI) | 69.0% | Not measured | Only Nemotron 3 Ultra measured |
| Vibe Code Bench (Vals AI) | 7.6% | Not measured | Only Nemotron 3 Ultra measured |
| Code migration (Vals AI) | 4.9% | Not measured | Only Nemotron 3 Ultra measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Nemotron 3 Ultra measured |
| Terminal-Bench 2.1 (Vals AI) | 50.9% | Not measured | Only Nemotron 3 Ultra measured |
| SciCode | 40.3% | 48.0% | Solar Pro 4 |
| Terminal-Bench Hard (Artificial Analysis run) | 36.4% | Not measured | Only Nemotron 3 Ultra measured |
| FrontierCode | 13.6% | Not measured | Only Nemotron 3 Ultra measured |
| WeirdML | 43.5% | Not measured | Only Nemotron 3 Ultra measured |
| ALE-Bench | Not measured | 179.3 | Only Solar Pro 4 measured |
| LMArena Text: coding | 1468 | 1438 | Nemotron 3 Ultra |
| LMArena Text: software and IT | 1468 | 1431 | Nemotron 3 Ultra |
| 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 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.9 | 28.2 | Solar Pro 4 |
| Epoch Capabilities Index | 146.0 | Not measured | Only Nemotron 3 Ultra measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 20.1 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: agents building web apps | Not measured | 1105 | Only Solar Pro 4 measured |
| Finance Agent (Vals AI) | 37.7% | Not measured | Only Nemotron 3 Ultra measured |
| Legal Research Bench (Vals AI) | 15.4% | Not measured | Only Nemotron 3 Ultra measured |
| Excel Modeling Benchmark (Vals AI) | 31.7% | Not measured | Only Nemotron 3 Ultra measured |
| τ²-Bench Telecom | 83.3% | Not measured | Only Nemotron 3 Ultra measured |
| APEX-Agents | 22.7% | Not measured | Only Nemotron 3 Ultra measured |
| MCP Atlas | 63.1% | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| GPQA Diamond | 86.1% | Not measured | Only Nemotron 3 Ultra measured |
| GPQA Diamond (Artificial Analysis run) | 86.7% | 89.1% | Solar Pro 4 |
| Humanity's Last Exam (Artificial Analysis run) | 28.4% | 29.8% | Solar Pro 4 |
| GPQA Diamond (Epoch AI run) | 85.4% | Not measured | Only Nemotron 3 Ultra measured |
| Mystery game puzzles | 20.0% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: hard prompts | 1452 | 1400 | Nemotron 3 Ultra |
| LMArena Text: expert | 1472 | 1428 | Nemotron 3 Ultra |
| LMArena Text: hard prompts in English | 1453 | 1427 | Nemotron 3 Ultra |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.7% | Not measured | Only Nemotron 3 Ultra measured |
| ProofBench | 2.0% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: math | 1457 | 1421 | Nemotron 3 Ultra |
| LMArena Text: mathematical work | 1461 | 1427 | Nemotron 3 Ultra |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| MMLU Pro | 85.8% | Not measured | Only Nemotron 3 Ultra measured |
| LegalBench (Vals AI) | 82.1% | Not measured | Only Nemotron 3 Ultra measured |
| CorpFin (Vals AI) | 65.5% | Not measured | Only Nemotron 3 Ultra measured |
| TaxEval (Vals AI) | 73.1% | Not measured | Only Nemotron 3 Ultra measured |
| MedCode (Vals AI) | 38.6% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text: science | 1465 | 1404 | Nemotron 3 Ultra |
| LMArena Text: medicine and healthcare | 1456 | 1374 | Nemotron 3 Ultra |
| LMArena Text: legal and government | 1452 | 1383 | Nemotron 3 Ultra |
| LMArena Text: business and finance | 1434 | 1381 | Nemotron 3 Ultra |
| Neither model has a result on the other 11 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1145 | 1176 | Solar Pro 4 |
| Design Arena: UI components | 1135 | 1147 | Solar Pro 4 |
| Design Arena: game dev | 1138 | 1169 | Solar Pro 4 |
| Design Arena: data viz | 1141 | 1178 | Solar Pro 4 |
| Design Arena: 3D | 1131 | 1178 | Solar Pro 4 |
| Design Arena: all code categories | 1146 | 1182 | Solar Pro 4 |
| Design Arena: SVG | 1069 | Not measured | Only Nemotron 3 Ultra measured |
| Design Arena: ASCII art | 1100 | Not measured | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
| Benchmark | Nemotron 3 Ultra | Solar Pro 4 | Leader |
|---|---|---|---|
| IFBench | 81.4% | Not measured | Only Nemotron 3 Ultra measured |
| Long context reasoning (AA-LCR) | 79.3% | 70.7% | Nemotron 3 Ultra |
| DTBench | 90.1% | Not measured | Only Nemotron 3 Ultra measured |
| LMCA | 36.9% | Not measured | Only Nemotron 3 Ultra measured |
| LMArena Text | 1445 | 1388 | Nemotron 3 Ultra |
| LMArena Text: instruction following | 1418 | 1375 | Nemotron 3 Ultra |
| LMArena Text: creative writing | 1399 | 1317 | Nemotron 3 Ultra |
| LMArena Text: English | 1455 | 1414 | Nemotron 3 Ultra |
| LMArena Text: non-English | 1427 | 1363 | Nemotron 3 Ultra |
| LMArena Text: Chinese | 1497 | 1422 | Nemotron 3 Ultra |
| LMArena Text: German | 1472 | 1358 | Nemotron 3 Ultra |
| LMArena Text: Japanese | Not measured | 1320 | Only Solar Pro 4 measured |
| LMArena Text: Korean | 1384 | 1383 | Nemotron 3 Ultra |
| LMArena Text: French | 1472 | 1400 | Nemotron 3 Ultra |
| LMArena Text: Spanish | 1455 | 1409 | Nemotron 3 Ultra |
| LMArena Text: Russian | 1417 | 1357 | Nemotron 3 Ultra |
| LMArena Text: Polish | 1385 | 1304 | Nemotron 3 Ultra |
| LMArena Text: multi-turn | 1411 | 1385 | Nemotron 3 Ultra |
| LMArena Text: longer queries | 1437 | 1382 | Nemotron 3 Ultra |
| LMArena Text: writing and language | 1406 | 1344 | Nemotron 3 Ultra |
| LMArena Text: entertainment and media | 1397 | 1332 | Nemotron 3 Ultra |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Nemotron 3 Ultra | 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 | NVIDIA Nemotron 3 Ultra | Upstage Solar Pro 4 |
|---|---|---|
| Maker | NVIDIA | Upstage |
| Weights | Open weights | No public weights listed |
| Released | June 4, 2026 | August 10, 2026 |
| Context window | 262K | 524K |
| Input $/Mtok | $0.60 | $0.15 |
| Output $/Mtok | $2.40 | $0.60 |
| Coding index | 30.0 | Not benchmarked |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Nemotron 3 Ultra better than Solar Pro 4 for coding?
Only Nemotron 3 Ultra has a coding score, 30.0 on the Vibe Coding Index; Solar Pro 4 has none, so the two cannot be ranked on coding. Pick Solar Pro 4 for output tokens 4.0x cheaper ($0.60 vs $2.40 per million) and a larger context window (524K against 262K tokens).
Which is cheaper, Nemotron 3 Ultra or Solar Pro 4?
Nemotron 3 Ultra costs $0.60 per million input tokens and $2.40 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, Nemotron 3 Ultra or Solar Pro 4?
Solar Pro 4, with 524K tokens against 262K.
How many benchmarks is the Nemotron 3 Ultra vs Solar Pro 4 comparison based on?
39 benchmarks have a result for both models as of October 22, 2026. Nemotron 3 Ultra's coding index rests on 3 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.