Model comparison
Command R vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.4 on the Noometry Index. Command R costs 4.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
Cohere
NVIDIASummary
- They share 18 benchmarks with published results for both. Command R scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 38.2.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 90.1% for Nemotron 3 Ultra.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 128K.
Side by side
| Command R | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Cohere | NVIDIA |
| Noometry Index | 31.4 | 42.5 |
| Released | 2024-08-30 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 128K | 262K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.15 | $0.60 |
| Output $ / M tokens | $0.60 | $2.40 |
| Results tracked | 29 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Command R: 29.3 (#306), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1169 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Command R: 13.8 (#331), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1452 |
| DTBench | 46.4% | 90.1% |
| LMCA | 9.2% | 36.9% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 21.9% | — |
| Mystery Game Puzzles | — | 20% |
| LiveBench Data Analysis | 33.3% | — |
| Epoch Capabilities Index | — | 146.17 |
| LiveBench | 27.5% | — |
Math Nemotron 3 Ultra leads
Command R: 28.0 (#246), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1155 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LiveBench Math | 19.4% | — |
Knowledge Nemotron 3 Ultra leads
Command R: 31.0 (#221), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1138 | 1472 |
| GPQA Diamond | — | 85.4% |
| MMLU | 65.2% | — |
Multilingual Nemotron 3 Ultra leads
Command R: 35.7 (#245), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1174 | 1427 |
| LMArena Chinese | 1182 | 1497 |
| LMArena French | 1162 | 1472 |
| LMArena German | 1176 | 1471 |
| LMArena Korean | 1163 | 1386 |
| LMArena Russian | 1174 | 1417 |
| LMArena Spanish | 1151 | 1454 |
| LMArena Japanese | 1143 | — |
Instruction Following Nemotron 3 Ultra leads
Command R: 58.1 (#261), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1167 | 1418 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Nemotron 3 Ultra leads
Command R: 36.3 (#231), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1198 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Command R: 38.2 (#254), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Command R | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1187 | 1445 |
| LMArena Creative Writing | 1170 | 1398 |
| LMArena Multi-Turn | 1163 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.4 on the Noometry Index. Command R costs 4.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Command R or Nemotron 3 Ultra?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is Command R or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 128K.
How many benchmarks do Command R and Nemotron 3 Ultra share?
18 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Nemotron 3 Ultra has 30.