Model comparison
MiMo-V2.5 vs Phi 3 Mini 4k Instruct
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 27.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. MiMo-V2.5 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 leads 61.8 to 27.7.
Side by side
| MiMo-V2.5 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 43.0 | 27.4 |
| Released | 2026-04-22 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.28 | — |
| Results tracked | 23 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.6 (#75), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1469 | 1093 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 513.95 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 27.8 (#98), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1072 |
| CritPt | 3.7% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math MiMo-V2.5 leads
MiMo-V2.5: 35.4 (#145), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1436 | 1111 |
| ProofBench | 16% | — |
| LiveBench Math | — | 15.7% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.2 (#109), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1459 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multimodal Not comparable
MiMo-V2.5: 39.0 (#53), Phi 3 Mini 4k Instruct: —
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 52.0 (#96), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1404 | 1021 |
| LMArena Chinese | 1467 | 1021 |
| LMArena French | 1447 | 1075 |
| LMArena German | 1421 | 1044 |
| LMArena Japanese | 1304 | 935 |
| LMArena Korean | 1363 | 905 |
| LMArena Russian | 1395 | 1022 |
| LMArena Spanish | 1412 | 1084 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.7 (#55), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1433 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.1 (#69), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1444 | 1044 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.8 (#82), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | MiMo-V2.5 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1427 | 1073 |
| LMArena Creative Writing | 1392 | 1037 |
| LMArena Multi-Turn | 1445 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is MiMo-V2.5 better than Phi 3 Mini 4k Instruct?
MiMo-V2.5 is the stronger model overall, scoring 43.0 to 27.4 on the Noometry Index.
Is MiMo-V2.5 or Phi 3 Mini 4k Instruct better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 26.1 in the Noometry coding category.
How many benchmarks do MiMo-V2.5 and Phi 3 Mini 4k Instruct share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.