Model comparison
C4ai Aya Expanse 32b vs Yi-Lightning
Yi-Lightning is the stronger model overall, scoring 36.5 to 35.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
CohereSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b 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 50.4 to 42.4.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Yi-Lightning | |
|---|---|---|
| Provider | Cohere | 01.AI |
| Noometry Index | 35.3 | 36.5 |
| Released | 2024-10-24 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.3 (#227), Yi-Lightning: 27.0 (#315)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1197 | 1313 |
| Aider Polyglot | — | 12.9% |
Reasoning Yi-Lightning leads
C4ai Aya Expanse 32b: 22.3 (#183), Yi-Lightning: 24.9 (#137)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1302 |
Math Yi-Lightning leads
C4ai Aya Expanse 32b: 31.4 (#195), Yi-Lightning: 33.5 (#173)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Math | 1200 | 1300 |
Knowledge Yi-Lightning leads
C4ai Aya Expanse 32b: 32.6 (#202), Yi-Lightning: 34.8 (#182)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1182 | 1286 |
| Vectara Hallucination Rate | 10.9% | — |
Multilingual Yi-Lightning leads
C4ai Aya Expanse 32b: 38.5 (#225), Yi-Lightning: 42.4 (#191)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1213 | 1269 |
| LMArena Chinese | 1210 | 1320 |
| LMArena French | 1247 | 1304 |
| LMArena German | 1199 | 1267 |
| LMArena Japanese | 1163 | 1228 |
| LMArena Korean | 1158 | 1192 |
| LMArena Russian | 1227 | 1255 |
| LMArena Spanish | 1193 | 1315 |
Instruction Following Yi-Lightning leads
C4ai Aya Expanse 32b: 62.9 (#232), Yi-Lightning: 67.6 (#191)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1196 | 1278 |
Long Context Yi-Lightning leads
C4ai Aya Expanse 32b: 37.2 (#215), Yi-Lightning: 39.4 (#176)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1228 | 1297 |
Writing & Preference Yi-Lightning leads
C4ai Aya Expanse 32b: 42.4 (#230), Yi-Lightning: 50.4 (#178)
| Benchmark | C4ai Aya Expanse 32b | Yi-Lightning |
|---|---|---|
| LMArena Text | 1224 | 1302 |
| LMArena Creative Writing | 1200 | 1280 |
| LMArena Multi-Turn | 1190 | 1311 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Yi-Lightning?
Yi-Lightning is the stronger model overall, scoring 36.5 to 35.3 on the Noometry Index.
Is C4ai Aya Expanse 32b or Yi-Lightning better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.3 versus 27.0 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Yi-Lightning share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Yi-Lightning has 18.