Model comparison
Qwen1.5-32B vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
UpstageSummary
- They share 17 benchmarks with published results for both. Qwen1.5-32B scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Solar Pro4 leads 39.8 to 13.5.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Qwen1.5-32B | Solar Pro4 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Upstage |
| Noometry Index | 30.5 | 42.1 |
| Released | 2024-02-04 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Qwen1.5-32B: 31.7 (#282), Solar Pro4: 40.1 (#149)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1155 | 1437 |
| LMArena WebDev | — | 1371 |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Reasoning Solar Pro4 leads
Qwen1.5-32B: 21.8 (#212), Solar Pro4: 28.5 (#104)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1399 |
Math Solar Pro4 leads
Qwen1.5-32B: 33.0 (#207), Solar Pro4: 38.8 (#128)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1155 | 1416 |
Knowledge Solar Pro4 leads
Qwen1.5-32B: 13.5 (#296), Solar Pro4: 39.8 (#129)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1126 | 1427 |
| GPQA Diamond | 30.7% | — |
| MMLU | 74.4% | — |
Multilingual Solar Pro4 leads
Qwen1.5-32B: 31.4 (#259), Solar Pro4: 48.7 (#139)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1106 | 1361 |
| LMArena Chinese | 1177 | 1415 |
| LMArena French | 1101 | 1397 |
| LMArena German | 1058 | 1364 |
| LMArena Japanese | 1027 | 1309 |
| LMArena Korean | 1008 | 1382 |
| LMArena Russian | 1073 | 1360 |
| LMArena Spanish | 1089 | 1401 |
Instruction Following Solar Pro4 leads
Qwen1.5-32B: 57.7 (#265), Solar Pro4: 72.7 (#132)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1377 |
Long Context Solar Pro4 leads
Qwen1.5-32B: 34.7 (#246), Solar Pro4: 42.1 (#130)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1146 | 1381 |
Writing & Preference Solar Pro4 leads
Qwen1.5-32B: 34.2 (#271), Solar Pro4: 56.5 (#138)
| Benchmark | Qwen1.5-32B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1137 | 1386 |
| LMArena Creative Writing | 1083 | 1316 |
| LMArena Multi-Turn | 1140 | 1385 |
Frequently asked questions
Is Qwen1.5-32B better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.5 on the Noometry Index.
Is Qwen1.5-32B or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 31.7 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Solar Pro4 share?
17 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Solar Pro4 has 18.