Model comparison
Llama 3.1-405B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and MiMo-V2.5-Pro in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 38.9.
- The biggest single-benchmark swing is DTBench: 61.4% for Llama 3.1-405B and 84.5% for MiMo-V2.5-Pro.
Side by side
| Llama 3.1-405B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 30.7 | 45.2 |
| Released | 2024-07-23 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 42 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Llama 3.1-405B: 33.1 (#262), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1291 | 1503 |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| WeirdML | 21.4% | — |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), MiMo-V2.5-Pro: —
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning MiMo-V2.5-Pro leads
Llama 3.1-405B: 16.8 (#300), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1488 |
| DTBench | 61.4% | 84.5% |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| LMCA | — | 29.5% |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math MiMo-V2.5-Pro leads
Llama 3.1-405B: 18.4 (#290), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1281 | 1481 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| ProofBench | — | 22% |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge MiMo-V2.5-Pro leads
Llama 3.1-405B: 30.4 (#227), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1243 | 1503 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual MiMo-V2.5-Pro leads
Llama 3.1-405B: 40.7 (#214), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1248 | 1449 |
| LMArena Chinese | 1242 | 1507 |
| LMArena French | 1279 | 1488 |
| LMArena German | 1252 | 1458 |
| LMArena Japanese | 1208 | 1412 |
| LMArena Korean | 1184 | 1437 |
| LMArena Russian | 1265 | 1450 |
| LMArena Spanish | 1260 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Llama 3.1-405B: 65.9 (#214), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1259 | 1477 |
| IFEval | 81.1% | — |
Long Context MiMo-V2.5-Pro leads
Llama 3.1-405B: 38.4 (#197), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1266 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Llama 3.1-405B: 38.9 (#251), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Llama 3.1-405B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1284 | 1465 |
| LMArena Creative Writing | 1262 | 1440 |
| EQ-Bench Creative Writing | 870 | 1493 |
| LMArena Multi-Turn | 1297 | 1477 |
| WildBench | 78.3% | — |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Llama 3.1-405B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and MiMo-V2.5-Pro share?
19 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and MiMo-V2.5-Pro has 27.