Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiMo-V2-Flash
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and MiMo-V2-Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Flash leads 59.7 to 49.8.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.6 | 41.3 |
| Released | 2024-09-06 | 2025-12-16 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 22 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiMo-V2-Flash: 36.1 (#211)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Coding | 1309 | 1443 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1330 |
| SciCode | — | 25.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 737.95 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiMo-V2-Flash: 24.9 (#157)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1420 |
| CritPt | — | 0% |
Math MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiMo-V2-Flash: 38.3 (#139)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Math | 1288 | 1396 |
Knowledge MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiMo-V2-Flash: 39.7 (#131)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Expert | 1266 | 1425 |
Multilingual MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiMo-V2-Flash: 51.0 (#113)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1392 |
| LMArena Chinese | 1318 | 1462 |
| LMArena French | 1289 | 1429 |
| LMArena German | 1258 | 1395 |
| LMArena Japanese | 1228 | 1325 |
| LMArena Korean | 1209 | 1358 |
| LMArena Russian | 1289 | 1387 |
| LMArena Spanish | 1248 | 1420 |
Instruction Following MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiMo-V2-Flash: 73.5 (#120)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1392 |
Long Context MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiMo-V2-Flash: 43.0 (#110)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1409 |
Writing & Preference MiMo-V2-Flash leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiMo-V2-Flash: 59.7 (#106)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Flash |
|---|---|---|
| LMArena Text | 1294 | 1411 |
| LMArena Creative Writing | 1285 | 1375 |
| LMArena Multi-Turn | 1297 | 1404 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2-Flash?
MiMo-V2-Flash is the stronger model overall, scoring 41.3 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2-Flash better for coding?
MiMo-V2-Flash scores higher on coding benchmarks: 36.1 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2-Flash share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2-Flash has 21.