# MiMo-V2.6-Flash vs Nemotron 3 Ultra

> MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 42.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mimo-v2-6-flash-vs-nemotron-3-ultra
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. MiMo-V2.6-Flash scores higher in 6 categories and Nemotron 3 Ultra in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Flash leads 51.9 to 35.3.
- The biggest single-benchmark swing is ProofBench: 63% for MiMo-V2.6-Flash and 2% for Nemotron 3 Ultra.
- MiMo-V2.6-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- MiMo-V2.6-Flash accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| Provider | Xiaomi | NVIDIA |
| Noometry Index | 48.5 | 42.5 |
| Rank | 55 | 113 |
| Context | 1.05M | 262K |
| Input $/M | $0.14 | $0.60 |
| Output $/M | $0.28 | $2.40 |
| Weights | Open | Open |

## Coding

- MiMo-V2.6-Flash: 53.4 (#30)
- Nemotron 3 Ultra: 38.1 (#182)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 51.3% | 40.3% |
| LMArena Coding | 1504 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1637 | — |
| WeirdML | — | 43.5% |

## Agentic & Tool Use

- MiMo-V2.6-Flash: —
- Nemotron 3 Ultra: 23.4 (#126)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |

## Reasoning

- MiMo-V2.6-Flash: 36.5 (#66)
- Nemotron 3 Ultra: 31.0 (#82)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 12% | 3.1% |
| LMArena Hard Prompts | 1482 | 1452 |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |

## Math

- MiMo-V2.6-Flash: 51.9 (#52)
- Nemotron 3 Ultra: 35.3 (#187)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 63% | 2% |
| LMArena Math | 1468 | 1457 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |

## Knowledge

- MiMo-V2.6-Flash: 42.2 (#99)
- Nemotron 3 Ultra: 52.5 (#61)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Expert | 1501 | 1472 |
| GPQA Diamond | — | 85.4% |

## Multimodal

- MiMo-V2.6-Flash: 40.5 (#47)
- Nemotron 3 Ultra: —

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1259 | — |

## Multilingual

- MiMo-V2.6-Flash: 54.0 (#51)
- Nemotron 3 Ultra: 53.5 (#64)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1434 | 1427 |
| LMArena Chinese | 1511 | 1497 |
| LMArena French | 1475 | 1472 |
| LMArena Russian | 1409 | 1417 |
| LMArena Spanish | 1456 | 1454 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |

## Instruction Following

- MiMo-V2.6-Flash: 76.8 (#35)
- Nemotron 3 Ultra: 74.7 (#88)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1463 | 1418 |

## Long Context

- MiMo-V2.6-Flash: 44.8 (#57)
- Nemotron 3 Ultra: 43.9 (#81)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1463 | 1437 |

## Writing & Preference

- MiMo-V2.6-Flash: 63.1 (#67)
- Nemotron 3 Ultra: 66.3 (#36)

| Benchmark | MiMo-V2.6-Flash | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1455 | 1445 |
| LMArena Creative Writing | 1400 | 1398 |
| LMArena Multi-Turn | 1451 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |

## FAQ

### Is MiMo-V2.6-Flash better than Nemotron 3 Ultra?

MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 42.5 on the Noometry Index.

### Which is cheaper, MiMo-V2.6-Flash or Nemotron 3 Ultra?

MiMo-V2.6-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.

### Is MiMo-V2.6-Flash or Nemotron 3 Ultra better for coding?

MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 38.1 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Flash does, with 1.05M tokens against 262K.

### How many benchmarks do MiMo-V2.6-Flash and Nemotron 3 Ultra share?

17 benchmarks have published results for both models. MiMo-V2.6-Flash has 19 scored results on Noometry and Nemotron 3 Ultra has 30.