Model comparison
Phi 3 Small 8k Instruct vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. Phi 3 Small 8k Instruct scores higher in 1 category and Yi-Lightning in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 31.1.
- Phi 3 Small 8k Instruct has downloadable open weights; the other is API-only.
Side by side
| Phi 3 Small 8k Instruct | Yi-Lightning | |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 29.3 | 37.1 |
| Released | 2024-04-23 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Phi 3 Small 8k Instruct: 27.9 (#318), Yi-Lightning: 27.4 (#320)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1101 | 1312 |
| Aider Polyglot | — | 12.9% |
| LiveBench Coding | 20.3% | — |
Reasoning Yi-Lightning leads
Phi 3 Small 8k Instruct: 14.8 (#323), Yi-Lightning: 25.9 (#139)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1100 | 1302 |
| 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 Yi-Lightning leads
Phi 3 Small 8k Instruct: 27.6 (#248), Yi-Lightning: 36.2 (#172)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Math | 1151 | 1300 |
| LiveBench Math | 17.6% | — |
Knowledge Yi-Lightning leads
Phi 3 Small 8k Instruct: 29.1 (#240), Yi-Lightning: 35.4 (#185)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1067 | 1286 |
| ARC (AI2) Challenge | 90.7% | — |
| MMLU | 75.7% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 58.1% | — |
Multilingual Yi-Lightning leads
Phi 3 Small 8k Instruct: 28.5 (#272), Yi-Lightning: 42.2 (#196)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1058 | 1269 |
| LMArena Chinese | 1061 | 1320 |
| LMArena French | 1135 | 1305 |
| LMArena German | 1080 | 1267 |
| LMArena Japanese | 966 | 1228 |
| LMArena Korean | 894 | 1192 |
| LMArena Russian | 1111 | 1255 |
| LMArena Spanish | 1111 | 1315 |
Instruction Following Yi-Lightning leads
Phi 3 Small 8k Instruct: 51.9 (#292), Yi-Lightning: 67.4 (#196)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1087 | 1278 |
| LiveBench Instruction Following | 47.2% | — |
Long Context Yi-Lightning leads
Phi 3 Small 8k Instruct: 33.0 (#267), Yi-Lightning: 39.4 (#181)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1088 | 1297 |
Writing & Preference Yi-Lightning leads
Phi 3 Small 8k Instruct: 31.1 (#284), Yi-Lightning: 50.2 (#184)
| Benchmark | Phi 3 Small 8k Instruct | Yi-Lightning |
|---|---|---|
| LMArena Text | 1110 | 1302 |
| LMArena Creative Writing | 1083 | 1280 |
| LMArena Multi-Turn | 1068 | 1311 |
| LiveBench Language | 12.9% | — |
Frequently asked questions
Is Phi 3 Small 8k Instruct better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 29.3 on the Noometry Index.
Is Phi 3 Small 8k Instruct or Yi-Lightning better for coding?
They score almost the same on coding (27.9 vs 27.4); test both on your own repository before choosing.
How many benchmarks do Phi 3 Small 8k Instruct and Yi-Lightning share?
17 benchmarks have published results for both models. Phi 3 Small 8k Instruct has 32 scored results on Noometry and Yi-Lightning has 18.