Model comparison
DeepSeek V4.1 Flash vs MiMo-V2.6-Pro
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 50.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeekSummary
- They share 19 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 3 categories and MiMo-V2.6-Pro in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4.1 Flash leads 57.9 to 43.5.
- The biggest single-benchmark swing is APEX-Agents: 39.5% for DeepSeek V4.1 Flash and 59.5% for MiMo-V2.6-Pro.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 1M.
Side by side
| DeepSeek V4.1 Flash | MiMo-V2.6-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 52.8 | 50.3 |
| Released | 2026-09-09 | 2026-09-21 |
| Weights | Open | Open |
| Context window | 1M | 1.05M |
| Max output | 393K | 131K |
| Input $ / M tokens | $0.15 | $0.43 |
| Output $ / M tokens | $0.60 | $0.87 |
| Results tracked | 37 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
DeepSeek V4.1 Flash: 52.9 (#32), MiMo-V2.6-Pro: 55.5 (#23)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1619 | 1629 |
| SciCode | 51.9% | 60.9% |
| LMArena Coding | 1506 | 1534 |
| ALE-Bench | 1,092 | 1,158 |
Agentic & Tool Use MiMo-V2.6-Pro leads
DeepSeek V4.1 Flash: 31.2 (#69), MiMo-V2.6-Pro: 37.5 (#35)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 39.5% | 59.5% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), MiMo-V2.6-Pro: 43.1 (#50)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 14.3% | 26.6% |
| LMArena Hard Prompts | 1483 | 1512 |
| 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-V2.6-Pro: 54.5 (#45)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 54% | 70% |
| LMArena Math | 1477 | 1494 |
| 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-V2.6-Pro: 43.5 (#92)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1506 | 1543 |
| GPQA Diamond | 89.8% | — |
Multimodal MiMo-V2.6-Pro leads
DeepSeek V4.1 Flash: 39.1 (#61), MiMo-V2.6-Pro: 40.8 (#43)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | 1277 | 1264 |
| Furniture Assembly | 34.2% | — |
Multilingual MiMo-V2.6-Pro leads
DeepSeek V4.1 Flash: 55.0 (#35), MiMo-V2.6-Pro: 56.9 (#14)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1448 | 1474 |
| LMArena Chinese | 1497 | 1529 |
| LMArena Russian | 1471 | 1480 |
| LMArena French | 1452 | — |
| LMArena German | 1484 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1452 | — |
| LMArena Spanish | 1459 | — |
Instruction Following Too close to call
DeepSeek V4.1 Flash: 77.3 (#26), MiMo-V2.6-Pro: 78.2 (#12)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1474 | 1493 |
Long Context Too close to call
DeepSeek V4.1 Flash: 45.2 (#47), MiMo-V2.6-Pro: 46.0 (#27)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1475 | 1501 |
Writing & Preference MiMo-V2.6-Pro leads
DeepSeek V4.1 Flash: 65.4 (#48), MiMo-V2.6-Pro: 66.8 (#33)
| Benchmark | DeepSeek V4.1 Flash | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1462 | 1492 |
| LMArena Creative Writing | 1435 | 1468 |
| LMArena Multi-Turn | 1457 | 1464 |
| EQ-Bench Creative Writing | 1540 | — |
Frequently asked questions
Is DeepSeek V4.1 Flash better than MiMo-V2.6-Pro?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 50.3 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or MiMo-V2.6-Pro?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is DeepSeek V4.1 Flash or MiMo-V2.6-Pro better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 52.9 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4.1 Flash and MiMo-V2.6-Pro share?
19 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and MiMo-V2.6-Pro has 19.