Model comparison
Qwen Max vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 34.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen Max scores higher in 2 categories and Yi-Lightning in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Yi-Lightning leads 36.2 to 22.3.
- The biggest single-benchmark swing is Aider Polyglot: 21.8% for Qwen Max and 12.9% for Yi-Lightning.
Side by side
| Qwen Max | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 34.7 | 37.1 |
| Released | 2024-04-03 | 2024-12-02 |
| Weights | Proprietary | Proprietary |
| Context window | 33K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.60 | — |
| Output $ / M tokens | $6.40 | — |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
Qwen Max: 30.7 (#292), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| Aider Polyglot | 21.8% | 12.9% |
| LMArena Coding | 1288 | 1312 |
Reasoning Too close to call
Qwen Max: 25.1 (#151), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1302 |
Math Yi-Lightning leads
Qwen Max: 22.3 (#276), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Math | 1275 | 1300 |
| OTIS Mock AIME 2024-2025 | 16.1% | — |
| MATH Level 5 | 67.2% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Yi-Lightning leads
Qwen Max: 30.3 (#228), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1248 | 1286 |
| GPQA Diamond | 56.1% | — |
Multilingual Too close to call
Qwen Max: 41.8 (#202), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1263 | 1269 |
| LMArena Chinese | 1254 | 1320 |
| LMArena French | 1330 | 1305 |
| LMArena German | 1254 | 1267 |
| LMArena Japanese | 1205 | 1228 |
| LMArena Korean | 1142 | 1192 |
| LMArena Russian | 1274 | 1255 |
| LMArena Spanish | 1290 | 1315 |
Instruction Following Too close to call
Qwen Max: 66.5 (#208), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1262 | 1278 |
Long Context Too close to call
Qwen Max: 39.4 (#180), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1288 | 1297 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Yi-Lightning leads
Qwen Max: 47.8 (#205), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen Max | Yi-Lightning |
|---|---|---|
| LMArena Text | 1282 | 1302 |
| LMArena Creative Writing | 1248 | 1280 |
| LMArena Multi-Turn | 1277 | 1311 |
Frequently asked questions
Is Qwen Max better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 34.7 on the Noometry Index.
Is Qwen Max or Yi-Lightning better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen Max and Yi-Lightning share?
18 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Yi-Lightning has 18.