Model comparison
DeepSeek LLM 67B vs MiMo-V2-Omni
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 24.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeekSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and MiMo-V2-Omni in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2-Omni leads 39.9 to 7.1.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | MiMo-V2-Omni | |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Noometry Index | 24.8 | 42.9 |
| Released | 2023-11-29 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
DeepSeek LLM 67B: 31.3 (#273), MiMo-V2-Omni: 42.7 (#87)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Coding | 1096 | 1467 |
Reasoning MiMo-V2-Omni leads
DeepSeek LLM 67B: 15.9 (#300), MiMo-V2-Omni: 28.6 (#86)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1445 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math MiMo-V2-Omni leads
DeepSeek LLM 67B: 8.1 (#318), MiMo-V2-Omni: 36.4 (#112)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Math | 1108 | 1432 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge MiMo-V2-Omni leads
DeepSeek LLM 67B: 7.1 (#308), MiMo-V2-Omni: 39.9 (#114)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1449 |
Multimodal Not comparable
DeepSeek LLM 67B: —, MiMo-V2-Omni: 37.9 (#62)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Vision | — | 1228 |
Multilingual MiMo-V2-Omni leads
DeepSeek LLM 67B: 29.5 (#262), MiMo-V2-Omni: 52.0 (#97)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Non-English | 1073 | 1404 |
| LMArena Chinese | 1132 | 1469 |
| LMArena French | — | 1448 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1318 |
| LMArena Korean | — | 1355 |
| LMArena Russian | — | 1412 |
| LMArena Spanish | — | 1432 |
Instruction Following MiMo-V2-Omni leads
DeepSeek LLM 67B: 55.7 (#272), MiMo-V2-Omni: 75.4 (#62)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Instruction Following | 1079 | 1428 |
Long Context MiMo-V2-Omni leads
DeepSeek LLM 67B: 33.1 (#260), MiMo-V2-Omni: 44.1 (#72)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Longer Query | 1092 | 1442 |
Writing & Preference MiMo-V2-Omni leads
DeepSeek LLM 67B: 31.8 (#277), MiMo-V2-Omni: 61.6 (#83)
| Benchmark | DeepSeek LLM 67B | MiMo-V2-Omni |
|---|---|---|
| LMArena Text | 1105 | 1424 |
| LMArena Creative Writing | 1067 | 1393 |
| LMArena Multi-Turn | 1082 | 1446 |
Frequently asked questions
Is DeepSeek LLM 67B better than MiMo-V2-Omni?
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B 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 LLM 67B and MiMo-V2-Omni share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and MiMo-V2-Omni has 18.