Model comparison
DeepSeek-V3.1-Terminus vs MiMo-V2-Flash
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.8 on the Noometry Index. MiMo-V2-Flash costs 2.7× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and MiMo-V2-Flash in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 41.5 to 35.8.
- The biggest single-benchmark swing is SciCode: 40.6% for DeepSeek-V3.1-Terminus and 25.9% for MiMo-V2-Flash.
- MiMo-V2-Flash is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- MiMo-V2-Flash accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1-Terminus | MiMo-V2-Flash | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 42.6 | 40.8 |
| Released | 2025-09-22 | 2025-12-16 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.30 | $0.14 |
| Output $ / M tokens | $1 | $0.28 |
| Results tracked | 16 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), MiMo-V2-Flash: 35.8 (#205)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| SciCode | 40.6% | 25.9% |
| LMArena Coding | 1426 | 1443 |
| ALE-Bench | 745.17 | 737.95 |
| LMArena WebDev | — | 1330 |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), MiMo-V2-Flash: 24.1 (#155)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| CritPt | 1.7% | 0% |
| LMArena Hard Prompts | 1427 | 1420 |
| Kagi LLM Benchmark | 57.4% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 35.7 (#138), MiMo-V2-Flash: 35.6 (#141)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1402 | 1396 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, MiMo-V2-Flash: 39.1 (#126)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | — | 1425 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), MiMo-V2-Flash: 51.1 (#109)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1407 | 1391 |
| LMArena Russian | 1434 | 1387 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1429 |
| LMArena German | — | 1395 |
| LMArena Japanese | — | 1324 |
| LMArena Korean | — | 1358 |
| LMArena Spanish | — | 1420 |
Instruction Following Too close to call
DeepSeek-V3.1-Terminus: 74.4 (#96), MiMo-V2-Flash: 73.7 (#115)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1406 | 1392 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.5 (#88), MiMo-V2-Flash: 43.0 (#106)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1426 | 1409 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), MiMo-V2-Flash: 59.9 (#101)
| Benchmark | DeepSeek-V3.1-Terminus | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1420 | 1411 |
| LMArena Creative Writing | 1404 | 1375 |
| LMArena Multi-Turn | 1411 | 1404 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than MiMo-V2-Flash?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.8 on the Noometry Index. MiMo-V2-Flash costs 2.7× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or MiMo-V2-Flash?
MiMo-V2-Flash is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or MiMo-V2-Flash better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 35.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Flash does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and MiMo-V2-Flash share?
13 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and MiMo-V2-Flash has 21.