Model comparison
Qwen3-30B-A3B vs Solar Pro4
Solar Pro4 is the stronger model overall, scoring 41.5 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 2.4× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
UpstageSummary
- They share 17 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 2 categories and Solar Pro4 in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where Solar Pro4 leads 42.0 to 31.0.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- Solar Pro4 accepts more context: 524K tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3-30B-A3B | Solar Pro4 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Upstage |
| Noometry Index | 38.5 | 41.5 |
| Released | 2025-04-28 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 41K | 524K |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.12 | $0.30 |
| Output $ / M tokens | $0.50 | $1.20 |
| Results tracked | 32 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Solar Pro4 leads
Qwen3-30B-A3B: 37.0 (#188), Solar Pro4: 39.9 (#135)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Coding | 1416 | 1439 |
| LMArena WebDev | — | 1371 |
| SciCode | 33.3% | — |
| WeirdML | 29.8% | — |
Agentic & Tool Use Not comparable
Qwen3-30B-A3B: 29.5 (#75), Solar Pro4: —
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |
Reasoning Solar Pro4 leads
Qwen3-30B-A3B: 21.6 (#193), Solar Pro4: 27.3 (#107)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1398 | 1398 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 8% | — |
| DTBench | 69.3% | — |
| LMCA | 22.4% | — |
| Epoch Capabilities Index | 139.63 | — |
Math Too close to call
Qwen3-30B-A3B: 36.0 (#133), Solar Pro4: 36.1 (#129)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Math | 1394 | 1418 |
| MathArena Final-Answer Competitions | 47.8% | — |
| OTIS Mock AIME 2024-2025 | 70.3% | — |
Knowledge Qwen3-30B-A3B leads
Qwen3-30B-A3B: 41.7 (#96), Solar Pro4: 39.0 (#128)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1395 | 1421 |
| GPQA Diamond | 70.1% | — |
| Confabulations | 12.3% | — |
Multilingual Too close to call
Qwen3-30B-A3B: 49.8 (#126), Solar Pro4: 49.0 (#134)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1372 | 1362 |
| LMArena Chinese | 1434 | 1417 |
| LMArena French | 1419 | 1403 |
| LMArena German | 1379 | 1351 |
| LMArena Japanese | 1338 | 1300 |
| LMArena Korean | 1333 | 1383 |
| LMArena Russian | 1369 | 1360 |
| LMArena Spanish | 1403 | 1408 |
Instruction Following Too close to call
Qwen3-30B-A3B: 72.2 (#137), Solar Pro4: 72.8 (#128)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1364 | 1376 |
Long Context Solar Pro4 leads
Qwen3-30B-A3B: 31.0 (#278), Solar Pro4: 42.0 (#125)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1379 | 1379 |
| Fiction.LiveBench | 40.6% | — |
Writing & Preference Too close to call
Qwen3-30B-A3B: 55.9 (#138), Solar Pro4: 56.7 (#133)
| Benchmark | Qwen3-30B-A3B | Solar Pro4 |
|---|---|---|
| LMArena Text | 1384 | 1386 |
| LMArena Creative Writing | 1318 | 1313 |
| LMArena Multi-Turn | 1378 | 1391 |
| Short-Story Creative Writing | 75.3% | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Solar Pro4?
Solar Pro4 is the stronger model overall, scoring 41.5 to 38.5 on the Noometry Index. Qwen3-30B-A3B costs 2.4× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.
Which is cheaper, Qwen3-30B-A3B or Solar Pro4?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is Qwen3-30B-A3B or Solar Pro4 better for coding?
Solar Pro4 scores higher on coding benchmarks: 39.9 versus 37.0 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 41K.
How many benchmarks do Qwen3-30B-A3B and Solar Pro4 share?
17 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Solar Pro4 has 18.