Claude Sonnet 4.5 vs Nemotron 3 Ultra
Claude Sonnet 4.5 leads Nemotron 3 Ultra on coding, 39.5 to 30.0 on the Vibe Coding Index, and Nemotron 3 Ultra costs 6.3x less per output token ($2.40 vs $15.00 per million). Updated October 22, 2026; 56 benchmarks have a result for both.
Claude Sonnet 4.5 or Nemotron 3 Ultra: which to pick
Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra.
Pick Nemotron 3 Ultra for output tokens 6.3x cheaper ($2.40 vs $15.00 per million) and work measured by LiveCodeBench (Vals AI) or AA Intelligence Index, where it leads.
- Shared results
- 56
- Claude Sonnet 4.5 only
- 44
- Nemotron 3 Ultra only
- 15
- Like-for-like categories
- 8 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
Claude Sonnet 4.5
Claude Sonnet 4.5 scores 39.5 against 30.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 22.9 against 20.7.
Same board, both measured
Agentic work
AA Agentic Index
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 20.1 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
Nemotron 3 Ultra
Nemotron 3 Ultra leads, 86.1% against 81.6%.
Same board, both measured
Math
AIME
No call
Only Claude Sonnet 4.5 has a AIME result, 88.2%.
Directional only
Knowledge
MMLU Pro
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 87.4% against 85.8%.
Same board, both measured
Web design
Design Arena: websites
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 1189 against 1145.
Same board, both measured
Long documents
Listed context window
Claude Sonnet 4.5
Claude Sonnet 4.5 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3 Ultra
Claude Sonnet 4.5 $0.011, Nemotron 3 Ultra $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Sonnet 4.5 has the number, $1.16.
Directional only
At a glance
- Coding index
- Claude Sonnet 4.5 39.5 from 3 benchmarks, Nemotron 3 Ultra 30.0 from 3 benchmarks.
- Widest category
- Math, 6.9 points apart on average over 4 shared benchmarks.
- Widest single gap
- ProofBench: Claude Sonnet 4.5 19.0% against Nemotron 3 Ultra 2.0%, 17.0 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.5 $15.00 against Nemotron 3 Ultra $2.40 per million output tokens, 6.3x apart.
- Context window
- Claude Sonnet 4.5 takes 1M tokens, Nemotron 3 Ultra 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 | Claude Sonnet 4.5 | Bars | Nemotron 3 Ultra | Ties |
|---|---|---|---|---|
| Coding | 6 | 1 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 3 | 3 | ||
| Math | 2 | 2 | ||
| Knowledge | 5 | 4 | ||
| Web design | 8 | 0 | ||
| General | 11 | 7 | ||
| All shared boards | 36 | 20 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index61
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| SWE-bench Verified | 74.8% | Not measured | Only Claude Sonnet 4.5 measured |
| SWE-bench Multilingual | 67.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev | 1394 | Not measured | Only Claude Sonnet 4.5 measured |
| AA Coding Index | 52.1 | 49.3 | Claude Sonnet 4.5 |
| LiveCodeBench (Vals AI) | 73.0% | 86.0% | Nemotron 3 Ultra |
| SWE-bench Verified (Vals AI) | 70.0% | 69.0% | Claude Sonnet 4.5 |
| Vibe Code Bench (Vals AI) | 22.6% | 7.6% | Claude Sonnet 4.5 |
| Code migration (Vals AI) | Not measured | 4.9% | Only Nemotron 3 Ultra measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Nemotron 3 Ultra measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 50.9% | Only Nemotron 3 Ultra measured |
| SciCode | Not measured | 40.3% | Only Nemotron 3 Ultra measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 36.4% | Only Nemotron 3 Ultra measured |
| Terminal-Bench | 46.5% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierCode | Not measured | 13.6% | Only Nemotron 3 Ultra measured |
| GSO-Bench | 14.7% | Not measured | Only Claude Sonnet 4.5 measured |
| WeirdML | 47.7% | 43.5% | Claude Sonnet 4.5 |
| Cybench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: coding | 1488 | 1468 | Claude Sonnet 4.5 |
| LMArena Text: software and IT | 1473 | 1468 | Claude Sonnet 4.5 |
| LMArena WebDev: React | 1386 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev: HTML | 1399 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.7 | 22.9 | Nemotron 3 Ultra |
| Epoch Capabilities Index | 146.7 | 146.0 | Claude Sonnet 4.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Agentic Index | 15.8 | 20.1 | Nemotron 3 Ultra |
| Design Arena: agents building web apps | 1060 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building full-stack apps | 1050 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building mobile apps | 1136 | Not measured | Only Claude Sonnet 4.5 measured |
| Finance Agent (Vals AI) | Not measured | 37.7% | Only Nemotron 3 Ultra measured |
| Legal Research Bench (Vals AI) | Not measured | 15.4% | Only Nemotron 3 Ultra measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 31.7% | Only Nemotron 3 Ultra measured |
| τ²-Bench Telecom | Not measured | 83.3% | Only Nemotron 3 Ultra measured |
| APEX-Agents | Not measured | 22.7% | Only Nemotron 3 Ultra measured |
| METR time horizons | 67.4% | Not measured | Only Claude Sonnet 4.5 measured |
| Remote Labor Index | 2.1% | Not measured | Only Claude Sonnet 4.5 measured |
| GDPval | 42.5% | Not measured | Only Claude Sonnet 4.5 measured |
| DeepResearch Bench | 52.6% | Not measured | Only Claude Sonnet 4.5 measured |
| OSWorld | 62.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Vending-Bench 2 | $3,839 | Not measured | Only Claude Sonnet 4.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 73.2% | Not measured | Only Claude Sonnet 4.5 measured |
| MCP Atlas | 59.5% | 63.1% | Nemotron 3 Ultra |
| Neither model has a result on the other 25 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| GPQA Diamond | 81.6% | 86.1% | Nemotron 3 Ultra |
| MMMU Pro (Vals AI) | 79.3% | Not measured | Only Claude Sonnet 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 86.7% | Only Nemotron 3 Ultra measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 28.4% | Only Nemotron 3 Ultra measured |
| GPQA Diamond (Epoch AI run) | 82.3% | 85.4% | Nemotron 3 Ultra |
| ARC-AGI | 63.7% | Not measured | Only Claude Sonnet 4.5 measured |
| ARC-AGI-2 | 13.6% | Not measured | Only Claude Sonnet 4.5 measured |
| SimpleBench | 54.3% | Not measured | Only Claude Sonnet 4.5 measured |
| Chess puzzles | 10.0% | Not measured | Only Claude Sonnet 4.5 measured |
| Mystery game puzzles | 17.0% | 20.0% | Nemotron 3 Ultra |
| EBR-bench | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| VPCT | 39.8% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: hard prompts | 1462 | 1452 | Claude Sonnet 4.5 |
| LMArena Text: expert | 1483 | 1472 | Claude Sonnet 4.5 |
| LMArena Text: hard prompts in English | 1471 | 1453 | Claude Sonnet 4.5 |
| Kagi LLM Benchmark | 57.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 7 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AIME | 88.2% | Not measured | Only Claude Sonnet 4.5 measured |
| MGSM (Vals AI) | 94.3% | Not measured | Only Claude Sonnet 4.5 measured |
| OTIS Mock AIME | 77.8% | 86.7% | Nemotron 3 Ultra |
| FrontierMath, tiers 1 to 3 | 23.9% | Not measured | Only Claude Sonnet 4.5 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| ProofBench | 19.0% | 2.0% | Claude Sonnet 4.5 |
| MATH level 5 | 97.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: math | 1449 | 1457 | Nemotron 3 Ultra |
| LMArena Text: mathematical work | 1462 | 1461 | Claude Sonnet 4.5 |
| MathArena | 12.6% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index54
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| MMLU Pro | 87.4% | 85.8% | Claude Sonnet 4.5 |
| LegalBench (Vals AI) | 84.1% | 82.1% | Claude Sonnet 4.5 |
| CaseLaw (Vals AI) | 62.2% | Not measured | Only Claude Sonnet 4.5 measured |
| CorpFin (Vals AI) | 62.0% | 65.5% | Nemotron 3 Ultra |
| TaxEval (Vals AI) | 73.3% | 73.1% | Claude Sonnet 4.5 |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Claude Sonnet 4.5 measured |
| MedQA (Vals AI) | 94.7% | Not measured | Only Claude Sonnet 4.5 measured |
| MedCode (Vals AI) | 44.1% | 38.6% | Claude Sonnet 4.5 |
| SimpleQA Verified | 30.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: science | 1448 | 1465 | Nemotron 3 Ultra |
| LMArena Text: medicine and healthcare | 1444 | 1456 | Nemotron 3 Ultra |
| LMArena Text: legal and government | 1451 | 1452 | Nemotron 3 Ultra |
| LMArena Text: business and finance | 1440 | 1434 | Claude Sonnet 4.5 |
| FACTS Benchmark Suite | 40.6% | Not measured | Only Claude Sonnet 4.5 measured |
| PRBench Finance | 43.8% | Not measured | Only Claude Sonnet 4.5 measured |
| PRBench Legal | 40.8% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Design Arena: websites | 1189 | 1145 | Claude Sonnet 4.5 |
| Design Arena: UI components | 1170 | 1135 | Claude Sonnet 4.5 |
| Design Arena: game dev | 1166 | 1138 | Claude Sonnet 4.5 |
| Design Arena: data viz | 1167 | 1141 | Claude Sonnet 4.5 |
| Design Arena: 3D | 1157 | 1131 | Claude Sonnet 4.5 |
| Design Arena: all code categories | 1182 | 1146 | Claude Sonnet 4.5 |
| Design Arena: SVG | 1114 | 1069 | Claude Sonnet 4.5 |
| Design Arena: ASCII art | 1205 | 1100 | Claude Sonnet 4.5 |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index117
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 36.1% | Not measured | Only Claude Sonnet 4.5 measured |
| MedScribe (Vals AI) | 84.5% | Not measured | Only Claude Sonnet 4.5 measured |
| IFBench | Not measured | 81.4% | Only Nemotron 3 Ultra measured |
| Long context reasoning (AA-LCR) | Not measured | 79.3% | Only Nemotron 3 Ultra measured |
| DTBench | 83.2% | 90.1% | Nemotron 3 Ultra |
| LMCA | 38.8% | 36.9% | Claude Sonnet 4.5 |
| LMArena Text | 1438 | 1445 | Nemotron 3 Ultra |
| LMArena Text: instruction following | 1459 | 1418 | Claude Sonnet 4.5 |
| LMArena Text: creative writing | 1442 | 1399 | Claude Sonnet 4.5 |
| LMArena Text: English | 1450 | 1455 | Nemotron 3 Ultra |
| LMArena Text: non-English | 1425 | 1427 | Nemotron 3 Ultra |
| LMArena Text: Chinese | 1460 | 1497 | Nemotron 3 Ultra |
| LMArena Text: German | 1427 | 1472 | Nemotron 3 Ultra |
| LMArena Text: Japanese | 1390 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Korean | 1402 | 1384 | Claude Sonnet 4.5 |
| LMArena Text: French | 1459 | 1472 | Nemotron 3 Ultra |
| LMArena Text: Spanish | 1458 | 1455 | Claude Sonnet 4.5 |
| LMArena Text: Russian | 1437 | 1417 | Claude Sonnet 4.5 |
| LMArena Text: Polish | 1423 | 1385 | Claude Sonnet 4.5 |
| LMArena Text: multi-turn | 1465 | 1411 | Claude Sonnet 4.5 |
| LMArena Text: longer queries | 1475 | 1437 | Claude Sonnet 4.5 |
| LMArena Text: writing and language | 1442 | 1406 | Claude Sonnet 4.5 |
| LMArena Text: entertainment and media | 1428 | 1397 | Claude Sonnet 4.5 |
| LMArena Document | 1450 | Not measured | Only Claude Sonnet 4.5 measured |
| MultiChallenge | 55.3% | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Sonnet 4.5 | Nemotron 3 Ultra | 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
Nemotron 3 Ultra costs less
Repository review
50K input + 3K output tokens
Nemotron 3 Ultra costs less
Agent loop
200K input + 10K output tokens
Nemotron 3 Ultra 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 | Anthropic Claude Sonnet 4.5 | NVIDIA Nemotron 3 Ultra |
|---|---|---|
| Maker | Anthropic | NVIDIA |
| Weights | No public weights listed | Open weights |
| Released | September 29, 2025 | June 4, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $3.00 | $0.60 |
| Output $/Mtok | $15.00 | $2.40 |
| Coding index | 39.5 | 30.0 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $1.16 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.5 better than Nemotron 3 Ultra for coding?
Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra. Pick Nemotron 3 Ultra for output tokens 6.3x cheaper ($2.40 vs $15.00 per million) and work measured by LiveCodeBench (Vals AI) or AA Intelligence Index, where it leads.
Which is cheaper, Claude Sonnet 4.5 or Nemotron 3 Ultra?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for Claude Sonnet 4.5 only.
Which has the bigger context window, Claude Sonnet 4.5 or Nemotron 3 Ultra?
Claude Sonnet 4.5, with 1M tokens against 262K.
How many benchmarks is the Claude Sonnet 4.5 vs Nemotron 3 Ultra comparison based on?
56 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.5's coding index rests on 3 independent benchmarks and Nemotron 3 Ultra's on 3. Where only one model has a result, the page says so instead of naming a winner.