Model comparison
Llama 3-8B vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 25.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Llama 3-8B 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 7.8.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | MiMo-V2-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 25.5 | 43.0 |
| 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 | 34 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Llama 3-8B: 31.0 (#289), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1152 | 1476 |
| LMArena WebDev | — | 1433 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| ALE-Bench | — | 785.17 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning MiMo-V2-Pro leads
Llama 3-8B: 14.3 (#326), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math MiMo-V2-Pro leads
Llama 3-8B: 8.8 (#323), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1151 | 1447 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge MiMo-V2-Pro leads
Llama 3-8B: 7.8 (#308), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1113 | 1478 |
| GPQA Diamond | 26.1% | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual MiMo-V2-Pro leads
Llama 3-8B: 30.8 (#261), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1098 | 1416 |
| LMArena Chinese | 1076 | 1456 |
| LMArena French | 1159 | 1469 |
| LMArena German | 1104 | 1417 |
| LMArena Japanese | 967 | 1366 |
| LMArena Korean | 1004 | 1400 |
| LMArena Russian | 1109 | 1427 |
| LMArena Spanish | 1173 | 1457 |
Instruction Following MiMo-V2-Pro leads
Llama 3-8B: 58.4 (#260), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1127 | 1445 |
Long Context MiMo-V2-Pro leads
Llama 3-8B: 34.2 (#251), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1128 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Llama 3-8B: 37.5 (#256), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Llama 3-8B | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1166 | 1436 |
| LMArena Creative Writing | 1150 | 1415 |
| LMArena Multi-Turn | 1152 | 1456 |
Frequently asked questions
Is Llama 3-8B better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 25.5 on the Noometry Index.
Is Llama 3-8B or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 31.0 in the Noometry coding category.
How many benchmarks do Llama 3-8B and MiMo-V2-Pro share?
17 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and MiMo-V2-Pro has 23.