Model comparison
MiMo-V2.5 vs Nemotron 3 Super
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 40.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
NVIDIASummary
- They share 18 benchmarks with published results for both. MiMo-V2.5 scores higher in 7 categories and Nemotron 3 Super in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 28.6 to 18.7.
- The biggest single-benchmark swing is SciCode: 43.1% for MiMo-V2.5 and 36% for Nemotron 3 Super.
- Both cost about the same: $0.14 input and $0.28 output per million tokens.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.5 | Nemotron 3 Super | |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 43.4 | 40.1 |
| Released | 2026-04-22 | 2026-03-11 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.14 | $0.08 |
| Output $ / M tokens | $0.28 | $0.45 |
| Results tracked | 23 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Nemotron 3 Super: 39.4 (#158)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| SciCode | 43.1% | 36% |
| LMArena Coding | 1469 | 1403 |
| ALE-Bench | 513.95 | 213.9 |
| LMArena WebDev | 1438 | — |
| WeirdML | — | 38% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Nemotron 3 Super: 18.7 (#276)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| CritPt | 3.7% | 3.1% |
| LMArena Hard Prompts | 1450 | 1386 |
| NYT Connections (extended) | — | 15.4% |
Math Nemotron 3 Super leads
MiMo-V2.5: 36.8 (#163), Nemotron 3 Super: 39.6 (#101)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1436 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| ProofBench | 16% | — |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Nemotron 3 Super: 38.9 (#139)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1460 | 1398 |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Nemotron 3 Super: —
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Nemotron 3 Super: 48.4 (#144)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1404 | 1355 |
| LMArena Chinese | 1468 | 1432 |
| LMArena French | 1447 | 1405 |
| LMArena German | 1421 | 1341 |
| LMArena Russian | 1395 | 1336 |
| LMArena Spanish | 1416 | 1417 |
| LMArena Japanese | 1306 | — |
| LMArena Korean | 1363 | — |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Nemotron 3 Super: 71.2 (#154)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1434 | 1347 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Nemotron 3 Super: 41.5 (#139)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1445 | 1362 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Nemotron 3 Super: 55.9 (#140)
| Benchmark | MiMo-V2.5 | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1428 | 1378 |
| LMArena Creative Writing | 1393 | 1317 |
| LMArena Multi-Turn | 1445 | 1369 |
Frequently asked questions
Is MiMo-V2.5 better than Nemotron 3 Super?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 40.1 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; MiMo-V2.5 lists at $0.14 and $0.28.
Is MiMo-V2.5 or Nemotron 3 Super better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.5 and Nemotron 3 Super share?
18 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Nemotron 3 Super has 21.