Model comparison
MiMo-V2.6-Pro vs Phi-2
MiMo-V2.6-Pro has enough public results to be ranked (#49); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSide by side
| MiMo-V2.6-Pro | Phi-2 | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 50.3 | — |
| Released | 2026-09-21 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.43 | — |
| Output $ / M tokens | $0.87 | — |
| Results tracked | 19 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiMo-V2.6-Pro: 55.5 (#23), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| LMArena Coding | 1534 | — |
| ALE-Bench | 1,158 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
MiMo-V2.6-Pro: 37.5 (#35), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| APEX-Agents | 59.5% | — |
Reasoning Not comparable
MiMo-V2.6-Pro: 43.1 (#50), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| CritPt | 26.6% | — |
| LMArena Hard Prompts | 1512 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.94 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
MiMo-V2.6-Pro: 54.5 (#45), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| ProofBench | 70% | — |
| LMArena Math | 1494 | — |
Knowledge Not comparable
MiMo-V2.6-Pro: 43.5 (#92), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Expert | 1543 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual Not comparable
MiMo-V2.6-Pro: 56.9 (#14), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Non-English | 1474 | — |
| LMArena Chinese | 1529 | — |
| LMArena Russian | 1480 | — |
Instruction Following Not comparable
MiMo-V2.6-Pro: 78.2 (#12), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1493 | — |
Long Context Not comparable
MiMo-V2.6-Pro: 46.0 (#27), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1501 | — |
Writing & Preference Not comparable
MiMo-V2.6-Pro: 66.8 (#33), Phi-2: —
| Benchmark | MiMo-V2.6-Pro | Phi-2 |
|---|---|---|
| LMArena Text | 1492 | — |
| LMArena Creative Writing | 1468 | — |
| LMArena Multi-Turn | 1464 | — |
Frequently asked questions
Is MiMo-V2.6-Pro better than Phi-2?
MiMo-V2.6-Pro has enough public results to be ranked (#49); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do MiMo-V2.6-Pro and Phi-2 share?
0 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Phi-2 has 11.