Model comparison
DBRX vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Databricks
NVIDIASummary
- They share 17 benchmarks with published results for both. DBRX scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 14.9.
- The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 85.4% for Nemotron 3 Ultra.
Side by side
| DBRX | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Databricks | NVIDIA |
| Noometry Index | 29.4 | 42.5 |
| Released | 2024-03-27 | 2026-06-04 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 21 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
DBRX: 32.9 (#266), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1132 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |
Agentic & Tool Use Not comparable
DBRX: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
DBRX: 21.4 (#222), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1452 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Nemotron 3 Ultra leads
DBRX: 24.3 (#269), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1145 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| MATH Level 5 | 11.7% | — |
Knowledge Nemotron 3 Ultra leads
DBRX: 14.9 (#294), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 32.9% | 85.4% |
| LMArena Expert | 1076 | 1472 |
Multilingual Nemotron 3 Ultra leads
DBRX: 29.3 (#268), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1071 | 1427 |
| LMArena Chinese | 1068 | 1497 |
| LMArena French | 1096 | 1472 |
| LMArena German | 1057 | 1471 |
| LMArena Korean | 993 | 1386 |
| LMArena Russian | 1078 | 1417 |
| LMArena Spanish | 1064 | 1454 |
| LMArena Japanese | 990 | — |
Instruction Following Nemotron 3 Ultra leads
DBRX: 57.5 (#270), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1112 | 1418 |
Long Context Nemotron 3 Ultra leads
DBRX: 33.7 (#258), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1112 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
DBRX: 33.6 (#275), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | DBRX | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1119 | 1445 |
| LMArena Creative Writing | 1104 | 1398 |
| LMArena Multi-Turn | 1111 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is DBRX better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 29.4 on the Noometry Index.
Is DBRX or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 32.9 in the Noometry coding category.
How many benchmarks do DBRX and Nemotron 3 Ultra share?
17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Nemotron 3 Ultra has 30.