Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiMo-V2.6-Flash
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 37.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and MiMo-V2.6-Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.6-Flash leads 53.4 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.6 | 48.5 |
| Released | 2024-09-06 | 2026-09-21 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 22 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), MiMo-V2.6-Flash: 53.4 (#30)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Coding | 1309 | 1504 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1637 |
| SciCode | — | 51.3% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), MiMo-V2.6-Flash: 36.5 (#66)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1482 |
| CritPt | — | 12% |
Math MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), MiMo-V2.6-Flash: 51.9 (#52)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Math | 1288 | 1468 |
| ProofBench | — | 63% |
Knowledge MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), MiMo-V2.6-Flash: 42.2 (#99)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Expert | 1266 | 1501 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiMo-V2.6-Flash: 40.5 (#47)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), MiMo-V2.6-Flash: 54.0 (#51)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1434 |
| LMArena Chinese | 1318 | 1511 |
| LMArena French | 1289 | 1475 |
| LMArena Russian | 1289 | 1409 |
| LMArena Spanish | 1248 | 1456 |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
Instruction Following MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), MiMo-V2.6-Flash: 76.8 (#35)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1463 |
Long Context MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), MiMo-V2.6-Flash: 44.8 (#57)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1463 |
Writing & Preference MiMo-V2.6-Flash leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), MiMo-V2.6-Flash: 63.1 (#67)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2.6-Flash |
|---|---|---|
| LMArena Text | 1294 | 1455 |
| LMArena Creative Writing | 1285 | 1400 |
| LMArena Multi-Turn | 1297 | 1451 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2.6-Flash?
MiMo-V2.6-Flash is the stronger model overall, scoring 48.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2.6-Flash better for coding?
MiMo-V2.6-Flash scores higher on coding benchmarks: 53.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2.6-Flash share?
14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2.6-Flash has 19.