Model comparison
Phi-4 Mini vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 25.3.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Phi-4 Mini | Yi-Lightning | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 30.9 | 37.1 |
| Released | 2024-12-11 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.075 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 3 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi-4 Mini: 28.1 (#317), Yi-Lightning: 27.4 (#320)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| SciCode | 10.8% | — |
| LMArena Coding | — | 1312 |
Reasoning Yi-Lightning leads
Phi-4 Mini: 22.4 (#195), Yi-Lightning: 25.9 (#139)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1302 |
Math Not comparable
Phi-4 Mini: —, Yi-Lightning: 36.2 (#172)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| LMArena Math | — | 1300 |
Knowledge Yi-Lightning leads
Phi-4 Mini: 25.3 (#262), Yi-Lightning: 35.4 (#185)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1286 |
Multilingual Not comparable
Phi-4 Mini: —, Yi-Lightning: 42.2 (#196)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Not comparable
Phi-4 Mini: —, Yi-Lightning: 67.4 (#196)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | — | 1278 |
Long Context Not comparable
Phi-4 Mini: —, Yi-Lightning: 39.4 (#181)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | — | 1297 |
Writing & Preference Not comparable
Phi-4 Mini: —, Yi-Lightning: 50.2 (#184)
| Benchmark | Phi-4 Mini | Yi-Lightning |
|---|---|---|
| LMArena Text | — | 1302 |
| LMArena Creative Writing | — | 1280 |
| LMArena Multi-Turn | — | 1311 |
Frequently asked questions
Is Phi-4 Mini better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.9 on the Noometry Index.
Is Phi-4 Mini or Yi-Lightning better for coding?
They score almost the same on coding (28.1 vs 27.4); test both on your own repository before choosing.
How many benchmarks do Phi-4 Mini and Yi-Lightning share?
0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Yi-Lightning has 18.