Model comparison
MiMo-V2-Omni vs Qwen2.5 72B Instruct
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 31.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiMo-V2-Omni scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2-Omni leads 36.4 to 18.1.
- MiMo-V2-Omni is cheaper at $0.14 / $0.28 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- MiMo-V2-Omni accepts more context: 262K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| MiMo-V2-Omni | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Xiaomi | Alibaba (Qwen) |
| Noometry Index | 42.9 | 31.5 |
| Released | 2026-03-18 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 262K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.14 | $1.40 |
| Output $ / M tokens | $0.28 | $5.60 |
| Results tracked | 18 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Omni leads
MiMo-V2-Omni: 42.7 (#87), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1467 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
MiMo-V2-Omni: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning MiMo-V2-Omni leads
MiMo-V2-Omni: 28.6 (#86), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1445 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129.01 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math MiMo-V2-Omni leads
MiMo-V2-Omni: 36.4 (#112), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1432 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge MiMo-V2-Omni leads
MiMo-V2-Omni: 39.9 (#114), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1449 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
MiMo-V2-Omni: 37.9 (#62), Qwen2.5 72B Instruct: —
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1228 | — |
Multilingual MiMo-V2-Omni leads
MiMo-V2-Omni: 52.0 (#97), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1404 | 1252 |
| LMArena Chinese | 1469 | 1272 |
| LMArena French | 1448 | 1279 |
| LMArena German | 1398 | 1234 |
| LMArena Japanese | 1318 | 1180 |
| LMArena Korean | 1355 | 1188 |
| LMArena Russian | 1412 | 1264 |
| LMArena Spanish | 1432 | 1255 |
Instruction Following MiMo-V2-Omni leads
MiMo-V2-Omni: 75.4 (#62), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1428 | 1254 |
| IFEval | — | 80.6% |
Long Context MiMo-V2-Omni leads
MiMo-V2-Omni: 44.1 (#72), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1442 | 1282 |
Writing & Preference MiMo-V2-Omni leads
MiMo-V2-Omni: 61.6 (#83), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | MiMo-V2-Omni | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1424 | 1269 |
| LMArena Creative Writing | 1393 | 1221 |
| LMArena Multi-Turn | 1446 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is MiMo-V2-Omni better than Qwen2.5 72B Instruct?
MiMo-V2-Omni is the stronger model overall, scoring 42.9 to 31.5 on the Noometry Index.
Which is cheaper, MiMo-V2-Omni or Qwen2.5 72B Instruct?
MiMo-V2-Omni is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is MiMo-V2-Omni or Qwen2.5 72B Instruct better for coding?
MiMo-V2-Omni scores higher on coding benchmarks: 42.7 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Omni does, with 262K tokens against 131K.
How many benchmarks do MiMo-V2-Omni and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. MiMo-V2-Omni has 18 scored results on Noometry and Qwen2.5 72B Instruct has 43.