Model comparison
DeepSeek-V3.1-Terminus vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.1 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and MiMo-V2.5-Pro in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.4 to 42.0.
- The biggest single-benchmark swing is SciCode: 40.6% for DeepSeek-V3.1-Terminus and 50.2% for MiMo-V2.5-Pro.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 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-Terminus | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 43.1 | 45.2 |
| Released | 2025-09-22 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 164K | 1.05M |
| Max output | 147K | 131K |
| Input $ / M tokens | $0.27 | $0.43 |
| Output $ / M tokens | $1 | $0.87 |
| Results tracked | 16 | 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-Terminus: 42.0 (#113), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| SciCode | 40.6% | 50.2% |
| LMArena Coding | 1426 | 1503 |
| ALE-Bench | 745.17 | 899.8 |
| LMArena WebDev | — | 1479 |
Reasoning Too close to call
DeepSeek-V3.1-Terminus: 26.4 (#133), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 1.7% | 4% |
| LMArena Hard Prompts | 1426 | 1488 |
| DTBench | 81.3% | 84.5% |
| LMCA | 28.6% | 29.5% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 34.4% |
Math MiMo-V2.5-Pro leads
DeepSeek-V3.1-Terminus: 38.5 (#137), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1402 | 1481 |
| ProofBench | — | 22% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | — | 1503 |
Multilingual MiMo-V2.5-Pro leads
DeepSeek-V3.1-Terminus: 52.1 (#92), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1407 | 1449 |
| LMArena Russian | 1436 | 1450 |
| LMArena Chinese | — | 1507 |
| LMArena French | — | 1488 |
| LMArena German | — | 1458 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
| LMArena Spanish | — | 1471 |
Instruction Following MiMo-V2.5-Pro leads
DeepSeek-V3.1-Terminus: 74.0 (#106), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1404 | 1477 |
Long Context MiMo-V2.5-Pro leads
DeepSeek-V3.1-Terminus: 43.4 (#97), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1421 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
DeepSeek-V3.1-Terminus: 61.0 (#92), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1419 | 1465 |
| LMArena Creative Writing | 1403 | 1440 |
| LMArena Multi-Turn | 1411 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 43.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or MiMo-V2.5-Pro?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is DeepSeek-V3.1-Terminus or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 42.0 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-Terminus and MiMo-V2.5-Pro share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and MiMo-V2.5-Pro has 27.