Model comparison
Qwen2-72B vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
UpstageSummary
- They share 17 benchmarks with published results for both. Qwen2-72B 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 21.2.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| Qwen2-72B | Solar Pro4 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Upstage |
| Noometry Index | 30.0 | 42.1 |
| Released | 2024-06-07 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | — | 524K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 26 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Qwen2-72B: 29.1 (#310), Solar Pro4: 40.1 (#149)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1196 | 1437 |
| LMArena WebDev | — | 1371 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Solar Pro4: —
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Solar Pro4 leads
Qwen2-72B: 23.2 (#181), Solar Pro4: 28.5 (#104)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1399 |
| Epoch Capabilities Index | 125.28 | — |
Math Solar Pro4 leads
Qwen2-72B: 30.2 (#236), Solar Pro4: 38.8 (#128)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1235 | 1416 |
| MATH Level 5 | 39.1% | — |
Knowledge Solar Pro4 leads
Qwen2-72B: 21.2 (#275), Solar Pro4: 39.8 (#129)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1171 | 1427 |
| GPQA Diamond | 40.8% | — |
| MMLU | 82.4% | — |
Multilingual Solar Pro4 leads
Qwen2-72B: 35.9 (#244), Solar Pro4: 48.7 (#139)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1176 | 1361 |
| LMArena Chinese | 1240 | 1415 |
| LMArena French | 1170 | 1397 |
| LMArena German | 1151 | 1364 |
| LMArena Japanese | 1111 | 1309 |
| LMArena Korean | 1083 | 1382 |
| LMArena Russian | 1169 | 1360 |
| LMArena Spanish | 1169 | 1401 |
Instruction Following Solar Pro4 leads
Qwen2-72B: 61.7 (#241), Solar Pro4: 72.7 (#132)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1181 | 1377 |
Long Context Solar Pro4 leads
Qwen2-72B: 36.1 (#235), Solar Pro4: 42.1 (#130)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1192 | 1381 |
Writing & Preference Solar Pro4 leads
Qwen2-72B: 40.8 (#241), Solar Pro4: 56.5 (#138)
| Benchmark | Qwen2-72B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1203 | 1386 |
| LMArena Creative Writing | 1181 | 1316 |
| LMArena Multi-Turn | 1196 | 1385 |
Frequently asked questions
Is Qwen2-72B better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 30.0 on the Noometry Index.
Is Qwen2-72B or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Solar Pro4 share?
17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Solar Pro4 has 18.