Model comparison
MiMo-V2.6-Pro vs Nemotron 3 Ultra
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 42.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 8 categories and Nemotron 3 Ultra in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 35.3.
- The biggest single-benchmark swing is ProofBench: 70% for MiMo-V2.6-Pro and 2% for Nemotron 3 Ultra.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.6-Pro | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 50.3 | 42.5 |
| Released | 2026-09-21 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.43 | $0.50 |
| Output $ / M tokens | $0.87 | $2.20 |
| Results tracked | 19 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 60.9% | 40.3% |
| LMArena Coding | 1534 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1629 | — |
| WeirdML | — | 43.5% |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | 59.5% | 22.7% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 26.6% | 3.1% |
| LMArena Hard Prompts | 1512 | 1452 |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 70% | 2% |
| LMArena Math | 1494 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
Knowledge Nemotron 3 Ultra leads
MiMo-V2.6-Pro: 43.5 (#92), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1543 | 1472 |
| GPQA Diamond | — | 85.4% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Nemotron 3 Ultra: —
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1474 | 1427 |
| LMArena Chinese | 1529 | 1497 |
| LMArena Russian | 1480 | 1417 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Spanish | — | 1454 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1493 | 1418 |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1501 | 1437 |
Writing & Preference Too close to call
MiMo-V2.6-Pro: 66.8 (#33), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | MiMo-V2.6-Pro | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1492 | 1445 |
| LMArena Creative Writing | 1468 | 1398 |
| LMArena Multi-Turn | 1464 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is MiMo-V2.6-Pro better than Nemotron 3 Ultra?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 42.5 on the Noometry Index.
Which is cheaper, MiMo-V2.6-Pro or Nemotron 3 Ultra?
MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is MiMo-V2.6-Pro or Nemotron 3 Ultra better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.6-Pro and Nemotron 3 Ultra share?
16 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Nemotron 3 Ultra has 30.