Model comparison
Claude Opus 4.1 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.0 on the Noometry Index.
Last verified . 24 shared benchmarks.
NVIDIASummary
- They share 24 benchmarks with published results for both. Claude Opus 4.1 scores higher in 5 categories and Nemotron 3 Ultra in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Ultra leads 35.3 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 68.9% for Claude Opus 4.1 and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 200K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4.1 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 41.0 | 42.5 |
| Released | 2025-08-05 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $0.50 |
| Output $ / M tokens | $75 | $2.20 |
| Results tracked | 48 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.1 leads
Claude Opus 4.1: 44.4 (#73), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 45.9% | 43.5% |
| LMArena Coding | 1479 | 1468 |
| SWE-bench Verified | 73.3% | — |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1390 | — |
| SciCode | — | 40.3% |
| ALE-Bench | 674.77 | — |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 4.1 leads
Claude Opus 4.1: 35.0 (#41), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 22.7% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
Reasoning Claude Opus 4.1 leads
Claude Opus 4.1: 32.2 (#76), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| Chess Puzzles | 7% | 12% |
| LMArena Hard Prompts | 1443 | 1452 |
| Mystery Game Puzzles | 21% | 20% |
| DTBench | 80% | 90.1% |
| LMCA | 37.1% | 36.9% |
| Epoch Capabilities Index | 144.12 | 146.17 |
| SimpleBench | 60% | — |
| CritPt | — | 3.1% |
| EnigmaEval | 7.2% | — |
| EBR-Bench | 7.9% | — |
| ForecastBench | 62 | — |
Math Nemotron 3 Ultra leads
Claude Opus 4.1: 22.3 (#277), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 86.7% |
| LMArena Math | 1431 | 1457 |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | — | 2% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Nemotron 3 Ultra leads
Claude Opus 4.1: 42.0 (#101), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 77.3% | 85.4% |
| LMArena Expert | 1439 | 1472 |
| Humanity's Last Exam | 11.5% | — |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Not comparable
Claude Opus 4.1: 26.8 (#119), Nemotron 3 Ultra: —
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| VPCT | 35% | — |
Multilingual Nemotron 3 Ultra leads
Claude Opus 4.1: 52.0 (#95), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1405 | 1427 |
| LMArena Chinese | 1427 | 1497 |
| LMArena French | 1431 | 1472 |
| LMArena German | 1413 | 1471 |
| LMArena Korean | 1380 | 1386 |
| LMArena Russian | 1422 | 1417 |
| LMArena Spanish | 1448 | 1454 |
| LMArena Japanese | 1378 | — |
Instruction Following Too close to call
Claude Opus 4.1: 75.6 (#58), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1435 | 1418 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1455 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Claude Opus 4.1: 62.4 (#74), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Claude Opus 4.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1419 | 1445 |
| LMArena Creative Writing | 1412 | 1398 |
| LMArena Multi-Turn | 1444 | 1411 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Claude Opus 4.1 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Nemotron 3 Ultra better for coding?
Claude Opus 4.1 scores higher on coding benchmarks: 44.4 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Nemotron 3 Ultra share?
24 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Nemotron 3 Ultra has 30.