Model comparison
Phi 3 Mini 4k Instruct vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Yi-Lightning in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 27.6.
- Phi 3 Mini 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Mini 4k Instruct | Yi-Lightning | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 27.9 | 37.1 |
| Released | 2024-04-23 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Mini 4k Instruct: 26.6 (#323), Yi-Lightning: 27.4 (#320)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1093 | 1312 |
| Aider Polyglot | — | 12.9% |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Yi-Lightning leads
Phi 3 Mini 4k Instruct: 14.1 (#328), Yi-Lightning: 25.9 (#139)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1302 |
| 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 Yi-Lightning leads
Phi 3 Mini 4k Instruct: 26.6 (#257), Yi-Lightning: 36.2 (#172)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Math | 1111 | 1300 |
| LiveBench Math | 15.7% | — |
Knowledge Yi-Lightning leads
Phi 3 Mini 4k Instruct: 28.5 (#246), Yi-Lightning: 35.4 (#185)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1045 | 1286 |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Yi-Lightning leads
Phi 3 Mini 4k Instruct: 26.3 (#280), Yi-Lightning: 42.2 (#196)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1021 | 1269 |
| LMArena Chinese | 1021 | 1320 |
| LMArena French | 1076 | 1305 |
| LMArena German | 1044 | 1267 |
| LMArena Japanese | 935 | 1228 |
| LMArena Korean | 905 | 1192 |
| LMArena Russian | 1022 | 1255 |
| LMArena Spanish | 1085 | 1315 |
Instruction Following Yi-Lightning leads
Phi 3 Mini 4k Instruct: 47.7 (#303), Yi-Lightning: 67.4 (#196)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1053 | 1278 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Yi-Lightning leads
Phi 3 Mini 4k Instruct: 31.7 (#276), Yi-Lightning: 39.4 (#181)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1044 | 1297 |
Writing & Preference Yi-Lightning leads
Phi 3 Mini 4k Instruct: 27.6 (#300), Yi-Lightning: 50.2 (#184)
| Benchmark | Phi 3 Mini 4k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Text | 1073 | 1302 |
| LMArena Creative Writing | 1037 | 1280 |
| LMArena Multi-Turn | 1018 | 1311 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 27.9 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Yi-Lightning better for coding?
They score almost the same on coding (26.6 vs 27.4); test both on your own repository before choosing.
How many benchmarks do Phi 3 Mini 4k Instruct and Yi-Lightning share?
17 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Yi-Lightning has 18.