Model comparison
Llama 3.2 3B vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 28.9 on the Noometry Index. Llama 3.2 3B costs 4.5× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
MetaSummary
- They share 14 benchmarks with published results for both. Llama 3.2 3B 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 24.7.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 131K.
Side by side
| Llama 3.2 3B | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Meta | Xiaomi |
| Noometry Index | 28.9 | 45.2 |
| Released | 2024-09-24 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 118K | 131K |
| Input $ / M tokens | $0.05 | $0.43 |
| Output $ / M tokens | $0.33 | $0.87 |
| Results tracked | 18 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Llama 3.2 3B: 27.6 (#319), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Coding | 1098 | 1503 |
| LMArena WebDev | — | 1479 |
| SciCode | — | 50.2% |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
| ALE-Bench | — | 899.8 |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), MiMo-V2.5-Pro: —
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning MiMo-V2.5-Pro leads
Llama 3.2 3B: 21.0 (#228), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1488 |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math MiMo-V2.5-Pro leads
Llama 3.2 3B: 32.4 (#214), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1126 | 1481 |
| ProofBench | — | 22% |
Knowledge MiMo-V2.5-Pro leads
Llama 3.2 3B: 29.7 (#235), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1090 | 1503 |
Multilingual MiMo-V2.5-Pro leads
Llama 3.2 3B: 26.2 (#281), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1019 | 1449 |
| LMArena Chinese | 1017 | 1507 |
| LMArena German | 1056 | 1458 |
| LMArena Russian | 949 | 1450 |
| LMArena French | — | 1488 |
| LMArena Japanese | — | 1412 |
| LMArena Korean | — | 1437 |
| LMArena Spanish | — | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Llama 3.2 3B: 56.0 (#275), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1089 | 1477 |
Long Context MiMo-V2.5-Pro leads
Llama 3.2 3B: 33.4 (#261), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1100 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Llama 3.2 3B: 24.7 (#307), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Llama 3.2 3B | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1110 | 1465 |
| LMArena Creative Writing | 1094 | 1440 |
| EQ-Bench Creative Writing | 595 | 1493 |
| LMArena Multi-Turn | 1105 | 1477 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Llama 3.2 3B better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 28.9 on the Noometry Index. Llama 3.2 3B costs 4.5× less per token, which makes it the better buy when MiMo-V2.5-Pro's lead doesn't matter for your workload.
Which is cheaper, Llama 3.2 3B or MiMo-V2.5-Pro?
Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; MiMo-V2.5-Pro lists at $0.43 and $0.87.
Is Llama 3.2 3B or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 27.6 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 131K.
How many benchmarks do Llama 3.2 3B and MiMo-V2.5-Pro share?
14 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and MiMo-V2.5-Pro has 27.