Model comparison
MiMo-V2.5 vs Phi 3 Small 8k Instruct
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.3 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 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 31.1.
Side by side
| MiMo-V2.5 | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 43.4 | 29.3 |
| 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 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1469 | 1101 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1100 |
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1436 | 1151 |
| ProofBench | 16% | — |
| LiveBench Math | — | 17.6% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1460 | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Phi 3 Small 8k Instruct: —
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1404 | 1058 |
| LMArena Chinese | 1468 | 1061 |
| LMArena French | 1447 | 1135 |
| LMArena German | 1421 | 1080 |
| LMArena Japanese | 1306 | 966 |
| LMArena Korean | 1363 | 894 |
| LMArena Russian | 1395 | 1111 |
| LMArena Spanish | 1416 | 1111 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1434 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1445 | 1088 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | MiMo-V2.5 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1428 | 1110 |
| LMArena Creative Writing | 1393 | 1083 |
| LMArena Multi-Turn | 1445 | 1068 |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is MiMo-V2.5 better than Phi 3 Small 8k Instruct?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 29.3 on the Noometry Index.
Is MiMo-V2.5 or Phi 3 Small 8k Instruct better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 27.9 in the Noometry coding category.
How many benchmarks do MiMo-V2.5 and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Phi 3 Small 8k Instruct has 32.