Model comparison
Qwen2.5 72B Instruct vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
UpstageSummary
- They share 17 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Solar Pro4 leads 38.8 to 19.3.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Solar Pro4 accepts more context: 524K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 72B Instruct | Solar Pro4 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Upstage |
| Noometry Index | 31.9 | 42.1 |
| Released | 2024-09 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 131K | 524K |
| Max output | 8K | 131K |
| Input $ / M tokens | $1.40 | $0.30 |
| Output $ / M tokens | $5.60 | $1.20 |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Qwen2.5 72B Instruct: 33.2 (#260), Solar Pro4: 40.1 (#149)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1292 | 1437 |
| LMArena WebDev | — | 1371 |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.1 (#133), Solar Pro4: —
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Solar Pro4 leads
Qwen2.5 72B Instruct: 22.3 (#199), Solar Pro4: 28.5 (#104)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1399 |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Solar Pro4 leads
Qwen2.5 72B Instruct: 19.3 (#287), Solar Pro4: 38.8 (#128)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Math | 1283 | 1416 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Solar Pro4 leads
Qwen2.5 72B Instruct: 27.0 (#253), Solar Pro4: 39.8 (#129)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1245 | 1427 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Solar Pro4 leads
Qwen2.5 72B Instruct: 41.0 (#213), Solar Pro4: 48.7 (#139)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1252 | 1361 |
| LMArena Chinese | 1272 | 1415 |
| LMArena French | 1280 | 1397 |
| LMArena German | 1234 | 1364 |
| LMArena Japanese | 1180 | 1309 |
| LMArena Korean | 1188 | 1382 |
| LMArena Russian | 1264 | 1360 |
| LMArena Spanish | 1256 | 1401 |
Instruction Following Solar Pro4 leads
Qwen2.5 72B Instruct: 65.5 (#221), Solar Pro4: 72.7 (#132)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1377 |
| IFEval | 80.6% | — |
Long Context Solar Pro4 leads
Qwen2.5 72B Instruct: 38.9 (#188), Solar Pro4: 42.1 (#130)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1282 | 1381 |
Writing & Preference Solar Pro4 leads
Qwen2.5 72B Instruct: 46.7 (#215), Solar Pro4: 56.5 (#138)
| Benchmark | Qwen2.5 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Text | 1269 | 1386 |
| LMArena Creative Writing | 1221 | 1316 |
| LMArena Multi-Turn | 1272 | 1385 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 42.1 to 31.9 on the Noometry Index.
Which is cheaper, Qwen2.5 72B Instruct or Solar Pro4?
Solar Pro4 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Qwen2.5 72B Instruct or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 40.1 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 131K.
How many benchmarks do Qwen2.5 72B Instruct and Solar Pro4 share?
17 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Solar Pro4 has 18.