Model comparison
Qwen1.5-32B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen1.5-32B scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Yi-Lightning leads 35.4 to 13.5.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen1.5-32B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 30.5 | 37.1 |
| Released | 2024-02-04 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Qwen1.5-32B: 31.7 (#282), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1155 | 1312 |
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Reasoning Yi-Lightning leads
Qwen1.5-32B: 21.8 (#212), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1302 |
Math Yi-Lightning leads
Qwen1.5-32B: 33.0 (#207), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1155 | 1300 |
Knowledge Yi-Lightning leads
Qwen1.5-32B: 13.5 (#296), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1126 | 1286 |
| GPQA Diamond | 30.7% | — |
| MMLU | 74.4% | — |
Multilingual Yi-Lightning leads
Qwen1.5-32B: 31.4 (#259), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1106 | 1269 |
| LMArena Chinese | 1177 | 1320 |
| LMArena French | 1101 | 1305 |
| LMArena German | 1058 | 1267 |
| LMArena Japanese | 1027 | 1228 |
| LMArena Korean | 1008 | 1192 |
| LMArena Russian | 1073 | 1255 |
| LMArena Spanish | 1089 | 1315 |
Instruction Following Yi-Lightning leads
Qwen1.5-32B: 57.7 (#265), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1116 | 1278 |
Long Context Yi-Lightning leads
Qwen1.5-32B: 34.7 (#246), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1146 | 1297 |
Writing & Preference Yi-Lightning leads
Qwen1.5-32B: 34.2 (#271), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen1.5-32B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1137 | 1302 |
| LMArena Creative Writing | 1083 | 1280 |
| LMArena Multi-Turn | 1140 | 1311 |
Frequently asked questions
Is Qwen1.5-32B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.5 on the Noometry Index.
Is Qwen1.5-32B or Yi-Lightning better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Yi-Lightning share?
17 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Yi-Lightning has 18.