# DeepSeek V4 Flash vs MiMo-V2.5

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-mimo-v2-5
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 6 categories and MiMo-V2.5 in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 27.8.
- The biggest single-benchmark swing is ProofBench: 56% for DeepSeek V4 Flash and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4 Flash.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 53.6 | 43.0 |
| Rank | 32 | 89 |
| Context | 1M | 1.05M |
| Input $/M | $0.15 | $0.14 |
| Output $/M | $0.60 | $0.28 |
| Weights | Open | Open |

## Coding

- DeepSeek V4 Flash: 47.6 (#56)
- MiMo-V2.5: 43.6 (#75)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1581 | 1438 |
| SciCode | 49.9% | 43.1% |
| LMArena Coding | 1457 | 1469 |
| ALE-Bench | 1,306 | 513.95 |
| FrontierCode | 18.8% | — |
| WeirdML | 63% | — |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#25)
- MiMo-V2.5: 27.8 (#98)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| CritPt | 16.6% | 3.7% |
| LMArena Hard Prompts | 1443 | 1450 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.51 | — |

## Math

- DeepSeek V4 Flash: 60.0 (#31)
- MiMo-V2.5: 35.4 (#145)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| ProofBench | 56% | 16% |
| LMArena Math | 1427 | 1436 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |

## Knowledge

- DeepSeek V4 Flash: 55.5 (#43)
- MiMo-V2.5: 40.2 (#109)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1441 | 1459 |
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |

## Multimodal

- DeepSeek V4 Flash: —
- MiMo-V2.5: 39.0 (#53)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- DeepSeek V4 Flash: 53.2 (#71)
- MiMo-V2.5: 52.0 (#96)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1420 | 1404 |
| LMArena Chinese | 1467 | 1467 |
| LMArena French | 1438 | 1447 |
| LMArena German | 1418 | 1421 |
| LMArena Japanese | 1403 | 1304 |
| LMArena Korean | 1383 | 1363 |
| LMArena Russian | 1428 | 1395 |
| LMArena Spanish | 1437 | 1412 |

## Instruction Following

- DeepSeek V4 Flash: 75.1 (#76)
- MiMo-V2.5: 75.7 (#55)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1421 | 1433 |

## Long Context

- DeepSeek V4 Flash: 43.8 (#81)
- MiMo-V2.5: 44.1 (#69)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1435 | 1444 |

## Writing & Preference

- DeepSeek V4 Flash: 64.0 (#59)
- MiMo-V2.5: 61.8 (#82)

| Benchmark | DeepSeek V4 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1432 | 1427 |
| LMArena Creative Writing | 1403 | 1392 |
| LMArena Multi-Turn | 1449 | 1445 |
| EQ-Bench Creative Writing | 1559 | — |

## FAQ

### Is DeepSeek V4 Flash better than MiMo-V2.5?

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.0 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Flash or MiMo-V2.5?

MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; DeepSeek V4 Flash lists at $0.15 and $0.60.

### Is DeepSeek V4 Flash or MiMo-V2.5 better for coding?

DeepSeek V4 Flash scores higher on coding benchmarks: 47.6 versus 43.6 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5 does, with 1.05M tokens against 1M.

### How many benchmarks do DeepSeek V4 Flash and MiMo-V2.5 share?

22 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and MiMo-V2.5 has 23.