Model comparison
Llama 2-13B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. Llama 2-13B 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 65.5 to 30.0.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 84.5% for MiMo-V2.5-Pro.
Side by side
| Llama 2-13B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 29.1 | 44.8 |
| Released | 2023-07-18 | 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 | 32 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Llama 2-13B: 30.4 (#287), MiMo-V2.5-Pro: 47.0 (#58)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1062 | 1502 |
| LMArena WebDev | — | 1477 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |
Reasoning MiMo-V2.5-Pro leads
Llama 2-13B: 12.3 (#333), MiMo-V2.5-Pro: 25.9 (#124)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1487 |
| DTBench | 42.2% | 84.5% |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 0% | — |
| LMCA | — | 29.5% |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math MiMo-V2.5-Pro leads
Llama 2-13B: 28.7 (#226), MiMo-V2.5-Pro: 38.6 (#84)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1065 | 1480 |
| ProofBench | — | 22% |
| GSM8K | 36.9% | — |
Knowledge MiMo-V2.5-Pro leads
Llama 2-13B: 27.5 (#244), MiMo-V2.5-Pro: 41.5 (#100)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1030 | 1501 |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, MiMo-V2.5-Pro: —
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual MiMo-V2.5-Pro leads
Llama 2-13B: 26.7 (#274), MiMo-V2.5-Pro: 55.3 (#33)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1024 | 1449 |
| LMArena Chinese | 1001 | 1507 |
| LMArena French | 1043 | 1489 |
| LMArena German | 1009 | 1455 |
| LMArena Japanese | 894 | 1418 |
| LMArena Korean | 953 | 1436 |
| LMArena Russian | 1055 | 1450 |
| LMArena Spanish | 1086 | 1470 |
Instruction Following MiMo-V2.5-Pro leads
Llama 2-13B: 53.5 (#282), MiMo-V2.5-Pro: 77.6 (#21)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1046 | 1477 |
Long Context MiMo-V2.5-Pro leads
Llama 2-13B: 32.3 (#264), MiMo-V2.5-Pro: 45.4 (#38)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1064 | 1482 |
Writing & Preference MiMo-V2.5-Pro leads
Llama 2-13B: 30.0 (#284), MiMo-V2.5-Pro: 65.5 (#47)
| Benchmark | Llama 2-13B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1085 | 1465 |
| LMArena Creative Writing | 1047 | 1440 |
| LMArena Multi-Turn | 1050 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Llama 2-13B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 44.8 to 29.1 on the Noometry Index.
Is Llama 2-13B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.0 versus 30.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and MiMo-V2.5-Pro share?
18 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and MiMo-V2.5-Pro has 27.