Model comparison
Qwen2-72B vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen2-72B 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 21.2.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Qwen2-72B | Yi-Lightning | |
|---|---|---|
| Provider | Alibaba (Qwen) | 01.AI |
| Noometry Index | 30.0 | 37.1 |
| Released | 2024-06-07 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Qwen2-72B: 29.1 (#310), Yi-Lightning: 27.4 (#320)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1196 | 1312 |
| Aider Polyglot | — | 12.9% |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Yi-Lightning: —
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Yi-Lightning leads
Qwen2-72B: 23.2 (#181), Yi-Lightning: 25.9 (#139)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1302 |
| Epoch Capabilities Index | 125.28 | — |
Math Yi-Lightning leads
Qwen2-72B: 30.2 (#236), Yi-Lightning: 36.2 (#172)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Math | 1235 | 1300 |
| MATH Level 5 | 39.1% | — |
Knowledge Yi-Lightning leads
Qwen2-72B: 21.2 (#275), Yi-Lightning: 35.4 (#185)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1171 | 1286 |
| GPQA Diamond | 40.8% | — |
| MMLU | 82.4% | — |
Multilingual Yi-Lightning leads
Qwen2-72B: 35.9 (#244), Yi-Lightning: 42.2 (#196)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1176 | 1269 |
| LMArena Chinese | 1240 | 1320 |
| LMArena French | 1170 | 1305 |
| LMArena German | 1151 | 1267 |
| LMArena Japanese | 1111 | 1228 |
| LMArena Korean | 1083 | 1192 |
| LMArena Russian | 1169 | 1255 |
| LMArena Spanish | 1169 | 1315 |
Instruction Following Yi-Lightning leads
Qwen2-72B: 61.7 (#241), Yi-Lightning: 67.4 (#196)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1181 | 1278 |
Long Context Yi-Lightning leads
Qwen2-72B: 36.1 (#235), Yi-Lightning: 39.4 (#181)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1192 | 1297 |
Writing & Preference Yi-Lightning leads
Qwen2-72B: 40.8 (#241), Yi-Lightning: 50.2 (#184)
| Benchmark | Qwen2-72B | Yi-Lightning |
|---|---|---|
| LMArena Text | 1203 | 1302 |
| LMArena Creative Writing | 1181 | 1280 |
| LMArena Multi-Turn | 1196 | 1311 |
Frequently asked questions
Is Qwen2-72B better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 30.0 on the Noometry Index.
Is Qwen2-72B or Yi-Lightning better for coding?
Qwen2-72B scores higher on coding benchmarks: 29.1 versus 27.4 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Yi-Lightning share?
17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Yi-Lightning has 18.