Model comparison
MiMo-V2-Pro vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 42.4 on the Noometry Index. MiMo-V2-Pro costs 1.9× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. MiMo-V2-Pro scores higher in 3 categories and Nemotron 3 Ultra in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 40.8.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Pro | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 42.4 | 44.7 |
| Released | 2026-03-18 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.43 | $0.60 |
| Output $ / M tokens | $0.87 | $2.40 |
| Results tracked | 23 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
MiMo-V2-Pro: 43.4 (#76), Nemotron 3 Ultra: 37.7 (#174)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1476 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1433 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| ALE-Bench | 785.17 | — |
Reasoning Nemotron 3 Ultra leads
MiMo-V2-Pro: 21.3 (#200), Nemotron 3 Ultra: 30.3 (#78)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1452 |
| NYT Connections (extended) | 25.8% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Thematic Generalization | 45.9% | — |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.2 |
Math MiMo-V2-Pro leads
MiMo-V2-Pro: 36.7 (#104), Nemotron 3 Ultra: 34.4 (#160)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Math | 1447 | 1456 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
MiMo-V2-Pro: 40.8 (#106), Nemotron 3 Ultra: 52.5 (#56)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1479 | 1472 |
| GPQA Diamond | — | 85.4% |
Multilingual Too close to call
MiMo-V2-Pro: 52.9 (#77), Nemotron 3 Ultra: 53.7 (#61)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1416 | 1427 |
| LMArena Chinese | 1455 | 1498 |
| LMArena French | 1470 | 1475 |
| LMArena German | 1417 | 1471 |
| LMArena Korean | 1401 | 1387 |
| LMArena Russian | 1427 | 1415 |
| LMArena Spanish | 1458 | 1452 |
| LMArena Japanese | 1366 | — |
Instruction Following MiMo-V2-Pro leads
MiMo-V2-Pro: 76.2 (#46), Nemotron 3 Ultra: 74.9 (#84)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1444 | 1417 |
Long Context Nemotron 3 Ultra leads
MiMo-V2-Pro: 41.5 (#133), Nemotron 3 Ultra: 43.9 (#77)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1455 | 1437 |
| CL-bench | 15.7% | — |
| CL-bench Life | 6.9% | — |
Writing & Preference Nemotron 3 Ultra leads
MiMo-V2-Pro: 62.9 (#67), Nemotron 3 Ultra: 66.3 (#35)
| Benchmark | MiMo-V2-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1436 | 1444 |
| LMArena Creative Writing | 1415 | 1392 |
| LMArena Multi-Turn | 1456 | 1412 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is MiMo-V2-Pro better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 42.4 on the Noometry Index. MiMo-V2-Pro costs 1.9× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2-Pro or Nemotron 3 Ultra?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.
Is MiMo-V2-Pro or Nemotron 3 Ultra better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 37.7 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2-Pro and Nemotron 3 Ultra share?
16 benchmarks have published results for both models. MiMo-V2-Pro has 23 scored results on Noometry and Nemotron 3 Ultra has 29.