Model comparison
MiMo-V2.6-Pro vs Phi-4
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.2 on the Noometry Index. Phi-4 costs 6.2× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. MiMo-V2.6-Pro scores higher in 9 categories and Phi-4 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 20.8.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.43 / $0.87 for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 128K.
Side by side
| MiMo-V2.6-Pro | Phi-4 | |
|---|---|---|
| Provider | Xiaomi | Microsoft |
| Noometry Index | 50.3 | 31.2 |
| Released | 2026-09-21 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 1.05M | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.43 | $0.07 |
| Output $ / M tokens | $0.87 | $0.14 |
| Results tracked | 19 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 55.5 (#23), Phi-4: 34.4 (#239)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Coding | 1534 | 1231 |
| LMArena WebDev | 1629 | — |
| SciCode | 60.9% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 1,158 | — |
Agentic & Tool Use MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 37.5 (#35), Phi-4: 22.8 (#128)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| APEX-Agents | 59.5% | — |
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.1 (#50), Phi-4: 17.7 (#291)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1512 | 1220 |
| CritPt | 26.6% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 54.5 (#45), Phi-4: 20.8 (#285)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Math | 1494 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| ProofBench | 70% | — |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 43.5 (#92), Phi-4: 32.6 (#209)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Expert | 1543 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multimodal Not comparable
MiMo-V2.6-Pro: 40.8 (#43), Phi-4: —
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Vision | 1264 | — |
Multilingual MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 56.9 (#14), Phi-4: 37.2 (#237)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Non-English | 1474 | 1197 |
| LMArena Chinese | 1529 | 1212 |
| LMArena Russian | 1480 | 1209 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Spanish | — | 1234 |
Instruction Following MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 78.2 (#12), Phi-4: 60.4 (#251)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1493 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 46.0 (#27), Phi-4: 36.9 (#226)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1501 | 1217 |
Writing & Preference MiMo-V2.6-Pro leads
MiMo-V2.6-Pro: 66.8 (#33), Phi-4: 40.5 (#244)
| Benchmark | MiMo-V2.6-Pro | Phi-4 |
|---|---|---|
| LMArena Text | 1492 | 1217 |
| LMArena Creative Writing | 1468 | 1182 |
| LMArena Multi-Turn | 1464 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is MiMo-V2.6-Pro better than Phi-4?
MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 31.2 on the Noometry Index. Phi-4 costs 6.2× less per token, which makes it the better buy when MiMo-V2.6-Pro's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.6-Pro or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; MiMo-V2.6-Pro lists at $0.43 and $0.87.
Is MiMo-V2.6-Pro or Phi-4 better for coding?
MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.6-Pro does, with 1.05M tokens against 128K.
How many benchmarks do MiMo-V2.6-Pro and Phi-4 share?
12 benchmarks have published results for both models. MiMo-V2.6-Pro has 19 scored results on Noometry and Phi-4 has 37.