Model comparison
C4ai Aya Expanse 32b vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
UpstageSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Solar Pro4 leads 56.5 to 42.2.
- Solar Pro4 accepts more context: 524K tokens versus 128K.
- C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.
Side by side
| C4ai Aya Expanse 32b | Solar Pro4 | |
|---|---|---|
| Provider | Cohere | Upstage |
| Noometry Index | 35.9 | 42.1 |
| Released | 2024-10-24 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 128K | 524K |
| Max output | 4K | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
C4ai Aya Expanse 32b: 34.8 (#231), Solar Pro4: 40.1 (#149)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1197 | 1437 |
| LMArena WebDev | — | 1371 |
Reasoning Solar Pro4 leads
C4ai Aya Expanse 32b: 23.3 (#180), Solar Pro4: 28.5 (#104)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1399 |
Math Solar Pro4 leads
C4ai Aya Expanse 32b: 34.0 (#197), Solar Pro4: 38.8 (#128)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Math | 1200 | 1416 |
Knowledge Solar Pro4 leads
C4ai Aya Expanse 32b: 33.2 (#206), Solar Pro4: 39.8 (#129)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1182 | 1427 |
| Vectara Hallucination Rate | 10.9% | — |
Multilingual Solar Pro4 leads
C4ai Aya Expanse 32b: 38.4 (#230), Solar Pro4: 48.7 (#139)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1213 | 1361 |
| LMArena Chinese | 1211 | 1415 |
| LMArena French | 1248 | 1397 |
| LMArena German | 1199 | 1364 |
| LMArena Japanese | 1163 | 1309 |
| LMArena Korean | 1158 | 1382 |
| LMArena Russian | 1227 | 1360 |
| LMArena Spanish | 1193 | 1401 |
Instruction Following Solar Pro4 leads
C4ai Aya Expanse 32b: 62.6 (#237), Solar Pro4: 72.7 (#132)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1377 |
Long Context Solar Pro4 leads
C4ai Aya Expanse 32b: 37.2 (#220), Solar Pro4: 42.1 (#130)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1228 | 1381 |
Writing & Preference Solar Pro4 leads
C4ai Aya Expanse 32b: 42.2 (#235), Solar Pro4: 56.5 (#138)
| Benchmark | C4ai Aya Expanse 32b | Solar Pro4 |
|---|---|---|
| LMArena Text | 1224 | 1386 |
| LMArena Creative Writing | 1200 | 1316 |
| LMArena Multi-Turn | 1190 | 1385 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and Solar Pro4 share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Solar Pro4 has 18.