Model comparison
DeepSeek-V3.1 vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 42.2 on the Noometry Index.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and MiMo-V2.5-Pro in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where MiMo-V2.5-Pro leads 45.4 to 36.3.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 29.5% for MiMo-V2.5-Pro.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 164K.
Side by side
| DeepSeek-V3.1 | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 42.2 | 44.8 |
| Released | 2025-08-21 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $0.43 |
| Output $ / M tokens | $0.95 | $0.87 |
| Results tracked | 27 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
DeepSeek-V3.1: 39.8 (#140), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1417 | 1502 |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| WeirdML | 38.4% | — |
| ALE-Bench | — | 899.8 |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1487 |
| DTBench | 82.7% | 84.5% |
| LMCA | 24.3% | 29.5% |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math MiMo-V2.5-Pro leads
DeepSeek-V3.1: 36.1 (#125), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1420 | 1480 |
| ProofBench | — | 22% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1403 | 1501 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual MiMo-V2.5-Pro leads
DeepSeek-V3.1: 51.8 (#100), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1400 | 1449 |
| LMArena Chinese | 1470 | 1507 |
| LMArena French | 1447 | 1489 |
| LMArena German | 1412 | 1455 |
| LMArena Japanese | 1374 | 1418 |
| LMArena Korean | 1337 | 1436 |
| LMArena Russian | 1405 | 1450 |
| LMArena Spanish | 1429 | 1470 |
Instruction Following MiMo-V2.5-Pro leads
DeepSeek-V3.1: 74.1 (#105), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1400 | 1477 |
Long Context MiMo-V2.5-Pro leads
DeepSeek-V3.1: 36.3 (#227), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1422 | 1482 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference MiMo-V2.5-Pro leads
DeepSeek-V3.1: 60.5 (#93), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | DeepSeek-V3.1 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1420 | 1465 |
| LMArena Creative Writing | 1401 | 1440 |
| EQ-Bench Creative Writing | 1436 | 1493 |
| LMArena Multi-Turn | 1408 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is DeepSeek-V3.1 better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 42.2 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or MiMo-V2.5-Pro?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is DeepSeek-V3.1 or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 39.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and MiMo-V2.5-Pro share?
20 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and MiMo-V2.5-Pro has 27.