Model comparison
DeepSeek-V2.5 (Sep 2024) vs MiMo-V2-Omni
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 37.0 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 0 categories and MiMo-V2-Omni in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Omni leads 61.6 to 50.0.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 37.0 | 42.9 |
| Released | 2024-09-06 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), MiMo-V2-Omni: 42.7 (#87)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Coding | 1310 | 1467 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), MiMo-V2-Omni: 28.6 (#86)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1445 |
Math MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), MiMo-V2-Omni: 36.4 (#112)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Math | 1289 | 1432 |
Knowledge MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), MiMo-V2-Omni: 39.9 (#114)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Expert | 1266 | 1449 |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, MiMo-V2-Omni: 37.9 (#62)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Vision | — | 1228 |
Multilingual MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), MiMo-V2-Omni: 52.0 (#97)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Non-English | 1273 | 1404 |
| LMArena Chinese | 1317 | 1469 |
| LMArena French | 1288 | 1448 |
| LMArena German | 1258 | 1398 |
| LMArena Japanese | 1228 | 1318 |
| LMArena Korean | 1209 | 1355 |
| LMArena Russian | 1289 | 1412 |
| LMArena Spanish | 1248 | 1432 |
Instruction Following MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), MiMo-V2-Omni: 75.4 (#62)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Instruction Following | 1280 | 1428 |
Long Context MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), MiMo-V2-Omni: 44.1 (#72)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Longer Query | 1301 | 1442 |
Writing & Preference MiMo-V2-Omni leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), MiMo-V2-Omni: 61.6 (#83)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | MiMo-V2-Omni |
|---|---|---|
| LMArena Text | 1294 | 1424 |
| LMArena Creative Writing | 1285 | 1393 |
| LMArena Multi-Turn | 1297 | 1446 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than MiMo-V2-Omni?
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or MiMo-V2-Omni better for coding?
MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and MiMo-V2-Omni share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and MiMo-V2-Omni has 18.