# DeepSeek-V3.1-Terminus vs MiMo-V2-Pro

> DeepSeek-V3.1-Terminus and MiMo-V2-Pro score almost the same on the Noometry Index (42.6 vs 42.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-mimo-v2-pro
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and MiMo-V2-Pro in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1-Terminus leads 25.7 to 21.3.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2-Pro.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 42.6 | 42.4 |
| Rank | 96 | 102 |
| Context | 164K | 1.05M |
| Input $/M | $0.30 | $0.43 |
| Output $/M | $1 | $0.87 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- MiMo-V2-Pro: 43.4 (#76)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1426 | 1476 |
| ALE-Bench | 745.17 | 785.17 |
| LMArena WebDev | — | 1433 |
| SciCode | 40.6% | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- MiMo-V2-Pro: 21.3 (#200)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1457 |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 25.8% |
| CritPt | 1.7% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- MiMo-V2-Pro: 36.7 (#104)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1402 | 1447 |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- MiMo-V2-Pro: 40.8 (#106)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | — | 1479 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- MiMo-V2-Pro: 52.9 (#77)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1407 | 1416 |
| LMArena Russian | 1434 | 1427 |
| LMArena Chinese | — | 1455 |
| LMArena French | — | 1470 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1458 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- MiMo-V2-Pro: 76.2 (#46)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1406 | 1444 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- MiMo-V2-Pro: 41.5 (#133)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1426 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- MiMo-V2-Pro: 62.9 (#67)

| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1420 | 1436 |
| LMArena Creative Writing | 1404 | 1415 |
| LMArena Multi-Turn | 1411 | 1456 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than MiMo-V2-Pro?

DeepSeek-V3.1-Terminus and MiMo-V2-Pro score almost the same on the Noometry Index (42.6 vs 42.4), so choose on price, context window or the category you care about most.

### Which is cheaper, DeepSeek-V3.1-Terminus or MiMo-V2-Pro?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; MiMo-V2-Pro lists at $0.43 and $0.87.

### Is DeepSeek-V3.1-Terminus or MiMo-V2-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 41.5 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2-Pro does, with 1.05M tokens against 164K.

### How many benchmarks do DeepSeek-V3.1-Terminus and MiMo-V2-Pro share?

11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and MiMo-V2-Pro has 23.