Model comparison
MiMo-V2.5-Pro vs Phi 3 Mini 4k Instruct
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiMo-V2.5-Pro scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5-Pro leads 65.3 to 27.6.
Side by side
| MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 45.2 | 27.9 |
| Released | 2026-04-22 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 27 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 47.4 (#60), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1503 | 1093 |
| LMArena WebDev | 1479 | — |
| SciCode | 50.2% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 899.8 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 26.8 (#130), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1488 | 1072 |
| NYT Connections (extended) | 34.4% | — |
| CritPt | 4% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| DTBench | 84.5% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 29.5% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 40.0 (#96), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1481 | 1111 |
| ProofBench | 22% | — |
| LiveBench Math | — | 15.7% |
Knowledge MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 42.2 (#98), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1503 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 55.1 (#34), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1449 | 1021 |
| LMArena Chinese | 1507 | 1021 |
| LMArena French | 1488 | 1076 |
| LMArena German | 1458 | 1044 |
| LMArena Japanese | 1412 | 935 |
| LMArena Korean | 1437 | 905 |
| LMArena Russian | 1450 | 1022 |
| LMArena Spanish | 1471 | 1085 |
Instruction Following MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 77.5 (#21), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1477 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 45.4 (#37), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1483 | 1044 |
Writing & Preference MiMo-V2.5-Pro leads
MiMo-V2.5-Pro: 65.3 (#49), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | MiMo-V2.5-Pro | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1465 | 1073 |
| LMArena Creative Writing | 1440 | 1037 |
| LMArena Multi-Turn | 1477 | 1018 |
| EQ-Bench Creative Writing | 1493 | — |
| EQ-Bench 4 | 1208 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is MiMo-V2.5-Pro better than Phi 3 Mini 4k Instruct?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 27.9 on the Noometry Index.
Is MiMo-V2.5-Pro or Phi 3 Mini 4k Instruct better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 26.6 in the Noometry coding category.
How many benchmarks do MiMo-V2.5-Pro and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. MiMo-V2.5-Pro has 27 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.