Model comparison
DeepSeek V4.1 Flash vs MiMo-V2.5
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 43.4 on the Noometry Index.
Last verified . 23 shared benchmarks.
DeepSeekSummary
- They share 23 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and MiMo-V2.5 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 36.8.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 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 V4.1 Flash.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 1M.
Side by side
| DeepSeek V4.1 Flash | MiMo-V2.5 | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 52.8 | 43.4 |
| Released | 2026-09-09 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 1M | 1.05M |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.15 | $0.14 |
| Output $ / M tokens | $0.60 | $0.28 |
| Results tracked | 37 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), MiMo-V2.5: 43.9 (#81)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1619 | 1438 |
| SciCode | 51.9% | 43.1% |
| LMArena Coding | 1506 | 1469 |
| ALE-Bench | 1,092 | 513.95 |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: 31.2 (#69), MiMo-V2.5: —
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), MiMo-V2.5: 28.6 (#101)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| CritPt | 14.3% | 3.7% |
| LMArena Hard Prompts | 1483 | 1450 |
| NYT Connections (extended) | 89.6% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), MiMo-V2.5: 36.8 (#163)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| ProofBench | 54% | 16% |
| LMArena Math | 1477 | 1436 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), MiMo-V2.5: 40.8 (#115)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1506 | 1460 |
| GPQA Diamond | 89.8% | — |
Multimodal Too close to call
DeepSeek V4.1 Flash: 39.1 (#61), MiMo-V2.5: 39.8 (#54)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1277 | 1247 |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), MiMo-V2.5: 51.9 (#99)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1448 | 1404 |
| LMArena Chinese | 1497 | 1468 |
| LMArena French | 1452 | 1447 |
| LMArena German | 1484 | 1421 |
| LMArena Japanese | 1412 | 1306 |
| LMArena Korean | 1452 | 1363 |
| LMArena Russian | 1471 | 1395 |
| LMArena Spanish | 1459 | 1416 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), MiMo-V2.5: 75.5 (#60)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1434 |
Long Context Too close to call
DeepSeek V4.1 Flash: 45.2 (#47), MiMo-V2.5: 44.2 (#73)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1475 | 1445 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), MiMo-V2.5: 61.6 (#86)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1462 | 1428 |
| LMArena Creative Writing | 1435 | 1393 |
| LMArena Multi-Turn | 1457 | 1445 |
| EQ-Bench Creative Writing | 1540 | — |
Frequently asked questions
Is DeepSeek V4.1 Flash better than MiMo-V2.5?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 43.4 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 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 V4.1 Flash lists at $0.15 and $0.60.
Is DeepSeek V4.1 Flash or MiMo-V2.5 better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 43.9 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 V4.1 Flash and MiMo-V2.5 share?
23 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and MiMo-V2.5 has 23.