Model comparison
Llama 3-70B vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 28.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2-Pro leads 36.7 to 12.0.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | MiMo-V2-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 28.5 | 42.4 |
| Released | 2024-04-18 | 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 | 31 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Llama 3-70B: 35.3 (#215), MiMo-V2-Pro: 43.4 (#76)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1206 | 1476 |
| LMArena WebDev | — | 1433 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| ALE-Bench | — | 785.17 |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 20.9 (#132), MiMo-V2-Pro: —
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| Cybench | 5% | — |
Reasoning MiMo-V2-Pro leads
Llama 3-70B: 17.4 (#284), MiMo-V2-Pro: 21.3 (#200)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1457 |
| Kagi LLM Benchmark | 35.1% | — |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.91 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math MiMo-V2-Pro leads
Llama 3-70B: 12.0 (#299), MiMo-V2-Pro: 36.7 (#104)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1218 | 1447 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge MiMo-V2-Pro leads
Llama 3-70B: 20.8 (#272), MiMo-V2-Pro: 40.8 (#106)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1149 | 1479 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual MiMo-V2-Pro leads
Llama 3-70B: 33.8 (#246), MiMo-V2-Pro: 52.9 (#77)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1142 | 1416 |
| LMArena Chinese | 1114 | 1455 |
| LMArena French | 1231 | 1470 |
| LMArena German | 1169 | 1417 |
| LMArena Japanese | 1017 | 1366 |
| LMArena Korean | 1017 | 1401 |
| LMArena Russian | 1159 | 1427 |
| LMArena Spanish | 1241 | 1458 |
Instruction Following MiMo-V2-Pro leads
Llama 3-70B: 62.8 (#233), MiMo-V2-Pro: 76.2 (#46)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1194 | 1444 |
Long Context MiMo-V2-Pro leads
Llama 3-70B: 35.6 (#235), MiMo-V2-Pro: 41.5 (#133)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1174 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Llama 3-70B: 43.0 (#225), MiMo-V2-Pro: 62.9 (#67)
| Benchmark | Llama 3-70B | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1221 | 1436 |
| LMArena Creative Writing | 1210 | 1415 |
| LMArena Multi-Turn | 1223 | 1456 |
Frequently asked questions
Is Llama 3-70B better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 42.4 to 28.5 on the Noometry Index.
Is Llama 3-70B or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.4 versus 35.3 in the Noometry coding category.
How many benchmarks do Llama 3-70B and MiMo-V2-Pro share?
17 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and MiMo-V2-Pro has 23.