Model comparison
Command A vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.5 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
NVIDIASummary
- They share 19 benchmarks with published results for both. Command A scores higher in 2 categories and Nemotron 3 Ultra in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 47.6.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 90.1% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $2.50 / $10 for Command A.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 256K.
Side by side
| Command A | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Cohere | NVIDIA |
| Noometry Index | 36.5 | 42.5 |
| Released | 2025-03-13 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 8K | 128K |
| Input $ / M tokens | $2.50 | $0.50 |
| Output $ / M tokens | $10 | $2.20 |
| Results tracked | 24 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Command A: 27.2 (#322), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1330 | 1468 |
| FrontierCode | — | 13.6% |
| Aider Polyglot | 12% | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Nemotron 3 Ultra leads
Command A: 18.3 (#283), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1452 |
| DTBench | 61.3% | 90.1% |
| LMCA | 10.3% | 36.9% |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| Epoch Capabilities Index | — | 146.17 |
Math Too close to call
Command A: 36.2 (#171), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1300 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
Command A: 37.1 (#159), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1295 | 1472 |
| GPQA Diamond | — | 85.4% |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual Nemotron 3 Ultra leads
Command A: 45.3 (#170), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1313 | 1427 |
| LMArena Chinese | 1327 | 1497 |
| LMArena French | 1351 | 1472 |
| LMArena German | 1341 | 1471 |
| LMArena Korean | 1285 | 1386 |
| LMArena Russian | 1314 | 1417 |
| LMArena Spanish | 1347 | 1454 |
| LMArena Japanese | 1285 | — |
Instruction Following Nemotron 3 Ultra leads
Command A: 69.1 (#177), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1309 | 1418 |
Long Context Nemotron 3 Ultra leads
Command A: 40.6 (#151), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1334 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Command A: 47.6 (#208), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Command A | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1331 | 1445 |
| LMArena Creative Writing | 1319 | 1398 |
| EQ-Bench Creative Writing | 1145 | 1692 |
| LMArena Multi-Turn | 1339 | 1411 |
Frequently asked questions
Is Command A better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 36.5 on the Noometry Index.
Which is cheaper, Command A 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; Command A lists at $2.50 and $10.
Is Command A or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 256K.
How many benchmarks do Command A and Nemotron 3 Ultra share?
19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Nemotron 3 Ultra has 30.