Model comparison
Qwen2.5-VL 72B Instruct vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 41.5 to 29.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
UpstageSummary
- The widest gap is in reasoning, where Solar Pro4 leads 27.3 to 20.0.
- Solar Pro4 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Solar Pro4 accepts more context: 524K tokens versus 131K.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-VL 72B Instruct | Solar Pro4 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Upstage |
| Noometry Index | 29.4 | 41.5 |
| Released | 2024-09 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 131K | 524K |
| Max output | 8K | 131K |
| Input $ / M tokens | $2.80 | $0.30 |
| Output $ / M tokens | $8.40 | $1.20 |
| Results tracked | 6 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 39.9 (#135)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena WebDev | — | 1371 |
| LMArena Coding | — | 1439 |
Agentic & Tool Use Not comparable
Qwen2.5-VL 72B Instruct: 18.4 (#136), Solar Pro4: —
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| OSWorld | 5% | — |
Reasoning Solar Pro4 leads
Qwen2.5-VL 72B Instruct: 20.0 (#228), Solar Pro4: 27.3 (#107)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| Kagi LLM Benchmark | 36% | — |
| LMArena Hard Prompts | — | 1398 |
Math Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 36.1 (#129)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Math | — | 1418 |
Knowledge Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 39.0 (#128)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Expert | — | 1421 |
Multimodal Not comparable
Qwen2.5-VL 72B Instruct: 32.9 (#92), Solar Pro4: —
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Vision | 1107 | — |
| Video-MME | 73.5% | — |
| GeoBench | 62% | — |
| SpatialViz-Bench | 33.3% | — |
Multilingual Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 49.0 (#134)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Non-English | — | 1362 |
| LMArena Chinese | — | 1417 |
| LMArena French | — | 1403 |
| LMArena German | — | 1351 |
| LMArena Japanese | — | 1300 |
| LMArena Korean | — | 1383 |
| LMArena Russian | — | 1360 |
| LMArena Spanish | — | 1408 |
Instruction Following Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 72.8 (#128)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | — | 1376 |
Long Context Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 42.0 (#125)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | — | 1379 |
Writing & Preference Not comparable
Qwen2.5-VL 72B Instruct: —, Solar Pro4: 56.7 (#133)
| Benchmark | Qwen2.5-VL 72B Instruct | Solar Pro4 |
|---|---|---|
| LMArena Text | — | 1386 |
| LMArena Creative Writing | — | 1313 |
| LMArena Multi-Turn | — | 1391 |
Frequently asked questions
Is Qwen2.5-VL 72B Instruct better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 41.5 to 29.4 on the Noometry Index.
Which is cheaper, Qwen2.5-VL 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-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 131K.
How many benchmarks do Qwen2.5-VL 72B Instruct and Solar Pro4 share?
0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Solar Pro4 has 18.