Model comparison
Llama 2-70B vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 24.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2-Pro leads 41.4 to 7.4.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | MiMo-V2-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 24.4 | 43.0 |
| Released | 2023-07-18 | 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 | 35 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Llama 2-70B: 31.4 (#286), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1079 | 1476 |
| LMArena WebDev | — | 1433 |
| ALE-Bench | — | 785.17 |
Reasoning MiMo-V2-Pro leads
Llama 2-70B: 14.4 (#325), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math MiMo-V2-Pro leads
Llama 2-70B: 8.1 (#326), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1091 | 1447 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge MiMo-V2-Pro leads
Llama 2-70B: 7.4 (#310), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1039 | 1478 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual MiMo-V2-Pro leads
Llama 2-70B: 27.7 (#274), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1045 | 1416 |
| LMArena Chinese | 995 | 1456 |
| LMArena French | 1090 | 1469 |
| LMArena German | 1041 | 1417 |
| LMArena Japanese | 927 | 1366 |
| LMArena Korean | 964 | 1400 |
| LMArena Russian | 1083 | 1427 |
| LMArena Spanish | 1143 | 1457 |
Instruction Following MiMo-V2-Pro leads
Llama 2-70B: 54.9 (#278), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1071 | 1445 |
Long Context MiMo-V2-Pro leads
Llama 2-70B: 32.3 (#270), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1062 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Llama 2-70B: 32.3 (#279), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Llama 2-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1115 | 1436 |
| LMArena Creative Writing | 1075 | 1415 |
| LMArena Multi-Turn | 1088 | 1456 |
Frequently asked questions
Is Llama 2-70B better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 24.4 on the Noometry Index.
Is Llama 2-70B or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and MiMo-V2-Pro share?
17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and MiMo-V2-Pro has 23.