Model comparison
Deepseek Coder v2 vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 37.1 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Yi-Lightning in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Yi-Lightning leads 50.2 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Yi-Lightning | |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 35.9 | 37.1 |
| Released | 2024-06-17 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Yi-Lightning: 27.4 (#320)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1251 | 1312 |
| Aider Polyglot | — | 12.9% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Yi-Lightning leads
Deepseek Coder v2: 23.6 (#176), Yi-Lightning: 25.9 (#139)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1302 |
| WinoGrande | 83.7% | — |
Math Yi-Lightning leads
Deepseek Coder v2: 34.9 (#190), Yi-Lightning: 36.2 (#172)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Math | 1241 | 1300 |
| GSM8K | 94.5% | — |
Knowledge Yi-Lightning leads
Deepseek Coder v2: 32.3 (#212), Yi-Lightning: 35.4 (#185)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1181 | 1286 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Yi-Lightning leads
Deepseek Coder v2: 36.3 (#240), Yi-Lightning: 42.2 (#196)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1182 | 1269 |
| LMArena Chinese | 1201 | 1320 |
| LMArena French | 1185 | 1305 |
| LMArena German | 1164 | 1267 |
| LMArena Japanese | 1126 | 1228 |
| LMArena Korean | 1104 | 1192 |
| LMArena Russian | 1188 | 1255 |
| LMArena Spanish | 1153 | 1315 |
Instruction Following Yi-Lightning leads
Deepseek Coder v2: 61.7 (#242), Yi-Lightning: 67.4 (#196)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1180 | 1278 |
Long Context Yi-Lightning leads
Deepseek Coder v2: 37.0 (#224), Yi-Lightning: 39.4 (#181)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1219 | 1297 |
Writing & Preference Yi-Lightning leads
Deepseek Coder v2: 38.2 (#253), Yi-Lightning: 50.2 (#184)
| Benchmark | Deepseek Coder v2 | Yi-Lightning |
|---|---|---|
| LMArena Text | 1191 | 1302 |
| LMArena Creative Writing | 1120 | 1280 |
| LMArena Multi-Turn | 1177 | 1311 |
Frequently asked questions
Is Deepseek Coder v2 better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 37.1 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Yi-Lightning better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 27.4 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Yi-Lightning share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Yi-Lightning has 18.