Model comparison
Claude 3.7 Sonnet vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
NVIDIASummary
- They share 20 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 4 categories and Nemotron 3 Ultra in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 39.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 57.8% for Claude 3.7 Sonnet and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Claude 3.7 Sonnet | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 39.5 | 42.5 |
| Released | 2025-02-24 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 58 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 40.6 (#136), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1361 | 1468 |
| SWE-bench Verified | 61% | — |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| SciCode | — | 40.3% |
| GSO | 3.8% | — |
| WeirdML | — | 43.5% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 34.1 (#50), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
Reasoning Nemotron 3 Ultra leads
Claude 3.7 Sonnet: 18.6 (#277), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1452 |
| Epoch Capabilities Index | 141.16 | 146.17 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 36.9% |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 37.5 (#153), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 86.7% |
| LMArena Math | 1337 | 1457 |
| ProofBench | — | 2% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Nemotron 3 Ultra leads
Claude 3.7 Sonnet: 39.8 (#130), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 79.7% | 85.4% |
| LMArena Expert | 1321 | 1472 |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Not comparable
Claude 3.7 Sonnet: 33.7 (#95), Nemotron 3 Ultra: —
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| SpatialViz-Bench | 33.9% | — |
Multilingual Nemotron 3 Ultra leads
Claude 3.7 Sonnet: 44.1 (#179), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1296 | 1427 |
| LMArena Chinese | 1299 | 1497 |
| LMArena French | 1303 | 1472 |
| LMArena German | 1301 | 1471 |
| LMArena Korean | 1249 | 1386 |
| LMArena Russian | 1311 | 1417 |
| LMArena Spanish | 1298 | 1454 |
| LMArena Japanese | 1267 | — |
Instruction Following Nemotron 3 Ultra leads
Claude 3.7 Sonnet: 72.9 (#125), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1352 | 1418 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1373 | 1437 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Nemotron 3 Ultra leads
Claude 3.7 Sonnet: 54.4 (#150), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Claude 3.7 Sonnet | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1314 | 1445 |
| LMArena Creative Writing | 1332 | 1398 |
| EQ-Bench Creative Writing | 1412 | 1692 |
| LMArena Multi-Turn | 1339 | 1411 |
| Short-Story Creative Writing | 81.1% | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Nemotron 3 Ultra better for coding?
Claude 3.7 Sonnet scores higher on coding benchmarks: 40.6 versus 38.1 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Nemotron 3 Ultra share?
20 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Nemotron 3 Ultra has 30.