Model comparison
Qwen2.5-Coder-32B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 0 categories and Yi-Lightning in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 41.6.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Coder-32B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 33.4 | 37.1 |
| Released | 2024-09-18 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 33K | — |
| Max output | 29K | — |
| Input $ / M tokens | $0.66 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 31 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Yi-Lightning leads
Qwen2.5-Coder-32B: 22.6 (#333), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 16.4% | 12.9% |
| LMArena Coding | 1276 | 1312 |
| SWE-bench Verified (bash only) | 9% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Reasoning Yi-Lightning leads
Qwen2.5-Coder-32B: 21.2 (#225), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1302 |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.49 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Yi-Lightning leads
Qwen2.5-Coder-32B: 33.3 (#204), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1251 | 1300 |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |
Knowledge Yi-Lightning leads
Qwen2.5-Coder-32B: 33.4 (#203), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1221 | 1286 |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Yi-Lightning leads
Qwen2.5-Coder-32B: 37.8 (#235), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1205 | 1269 |
| LMArena Chinese | 1222 | 1320 |
| LMArena Russian | 1228 | 1255 |
| LMArena French | — | 1305 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Spanish | — | 1315 |
Instruction Following Yi-Lightning leads
Qwen2.5-Coder-32B: 61.4 (#245), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1223 | 1278 |
| LiveBench Instruction Following | 58.7% | — |
Long Context Yi-Lightning leads
Qwen2.5-Coder-32B: 38.0 (#208), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1251 | 1297 |
Writing & Preference Yi-Lightning leads
Qwen2.5-Coder-32B: 41.6 (#240), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen2.5-Coder-32B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1230 | 1302 |
| LMArena Creative Writing | 1174 | 1280 |
| LMArena Multi-Turn | 1222 | 1311 |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 33.4 on the Noometry Index.
Is Qwen2.5-Coder-32B or Yi-Lightning better for coding?
Yi-Lightning scores higher on coding benchmarks: 27.4 versus 22.6 in the Noometry coding category.
How many benchmarks do Qwen2.5-Coder-32B and Yi-Lightning share?
13 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Yi-Lightning has 18.