Model comparison
Llama 3.2 90B vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 27.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in math, where MiMo-V2-Pro leads 39.5 to 11.1.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | MiMo-V2-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 27.5 | 43.0 |
| Released | 2024-09-24 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 9 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | — | 1433 |
| LMArena Coding | — | 1476 |
| ALE-Bench | — | 785.17 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), MiMo-V2-Pro: —
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| BALROG | 27.3% | — |
Reasoning Too close to call
Llama 3.2 90B: 21.7 (#217), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| NYT Connections (extended) | — | 25.8% |
| EnigmaEval | 0.4% | — |
| Thematic Generalization | — | 45.9% |
| LMArena Hard Prompts | — | 1457 |
| Epoch Capabilities Index | 125.5 | — |
Math MiMo-V2-Pro leads
Llama 3.2 90B: 11.1 (#308), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1447 |
| MATH Level 5 | 39.4% | — |
Knowledge MiMo-V2-Pro leads
Llama 3.2 90B: 21.7 (#274), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1478 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), MiMo-V2-Pro: —
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | — | 1416 |
| LMArena Chinese | — | 1456 |
| LMArena French | — | 1469 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
| LMArena Korean | — | 1400 |
| LMArena Russian | — | 1427 |
| LMArena Spanish | — | 1457 |
Instruction Following Not comparable
Llama 3.2 90B: —, MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | — | 1445 |
Long Context Not comparable
Llama 3.2 90B: —, MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Llama 3.2 90B: —, MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Llama 3.2 90B | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | — | 1436 |
| LMArena Creative Writing | — | 1415 |
| LMArena Multi-Turn | — | 1456 |
Frequently asked questions
Is Llama 3.2 90B better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and MiMo-V2-Pro share?
0 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and MiMo-V2-Pro has 23.