Model comparison
Qwen-14B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 1 category and Yi-Lightning in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Qwen-14B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 31.4 | 37.1 |
| Released | 2023-09-24 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Qwen-14B: 31.2 (#288), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1071 | 1312 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
Qwen-14B: 19.6 (#257), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1302 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Yi-Lightning leads
Qwen-14B: 31.2 (#227), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1068 | 1300 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Expert | — | 1286 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Yi-Lightning leads
Qwen-14B: 27.5 (#275), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1041 | 1269 |
| LMArena Chinese | 1077 | 1320 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Qwen-14B: 52.4 (#289), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1031 | 1278 |
Long Context Yi-Lightning leads
Qwen-14B: 31.3 (#280), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1028 | 1297 |
Writing & Preference Yi-Lightning leads
Qwen-14B: 27.6 (#299), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen-14B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1051 | 1302 |
| LMArena Creative Writing | 1028 | 1280 |
| LMArena Multi-Turn | 1022 | 1311 |
Frequently asked questions
Is Qwen-14B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 31.4 on the Noometry Index.
Is Qwen-14B or Yi-Lightning better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen-14B and Yi-Lightning share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Yi-Lightning has 18.