Model comparison
DeepSeek-V3.1 vs MiMo-V2.5
DeepSeek-V3.1 and MiMo-V2.5 score almost the same on the Noometry Index (42.8 vs 43.4), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and MiMo-V2.5 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiMo-V2.5 leads 44.2 to 36.3.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.25 / $0.95 for DeepSeek-V3.1.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-V3.1 | MiMo-V2.5 | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 42.8 | 43.4 |
| Released | 2025-08-21 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $0.14 |
| Output $ / M tokens | $0.95 | $0.28 |
| Results tracked | 27 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
DeepSeek-V3.1: 40.3 (#144), MiMo-V2.5: 43.9 (#81)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Coding | 1417 | 1469 |
| LMArena WebDev | — | 1438 |
| SciCode | — | 43.1% |
| WeirdML | 38.4% | — |
| ALE-Bench | — | 513.95 |
Reasoning Too close to call
DeepSeek-V3.1: 27.9 (#110), MiMo-V2.5: 28.6 (#101)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1450 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | — | 3.7% |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), MiMo-V2.5: 36.8 (#163)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1420 | 1436 |
| ProofBench | — | 16% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), MiMo-V2.5: 40.8 (#115)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1405 | 1460 |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
DeepSeek-V3.1: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Too close to call
DeepSeek-V3.1: 51.6 (#106), MiMo-V2.5: 51.9 (#99)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1400 | 1404 |
| LMArena Chinese | 1469 | 1468 |
| LMArena French | 1447 | 1447 |
| LMArena German | 1411 | 1421 |
| LMArena Japanese | 1378 | 1306 |
| LMArena Korean | 1337 | 1363 |
| LMArena Russian | 1405 | 1395 |
| LMArena Spanish | 1431 | 1416 |
Instruction Following MiMo-V2.5 leads
DeepSeek-V3.1: 73.9 (#110), MiMo-V2.5: 75.5 (#60)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1434 |
Long Context MiMo-V2.5 leads
DeepSeek-V3.1: 36.3 (#232), MiMo-V2.5: 44.2 (#73)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1445 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference MiMo-V2.5 leads
DeepSeek-V3.1: 60.3 (#98), MiMo-V2.5: 61.6 (#86)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1420 | 1428 |
| LMArena Creative Writing | 1401 | 1393 |
| LMArena Multi-Turn | 1408 | 1445 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than MiMo-V2.5?
DeepSeek-V3.1 and MiMo-V2.5 score almost the same on the Noometry Index (42.8 vs 43.4), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 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-V3.1 lists at $0.25 and $0.95.
Is DeepSeek-V3.1 or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and MiMo-V2.5 share?
17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and MiMo-V2.5 has 23.