Model comparison
Qwen3-30B-A3B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 3.3× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 2 categories and Qwen3.7 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Plus leads 39.3 to 22.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 70.3% for Qwen3-30B-A3B and 93.3% for Qwen3.7 Plus.
- Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus accepts more context: 1M tokens versus 41K.
- Qwen3-30B-A3B has downloadable open weights; the other is API-only.
Side by side
| Qwen3-30B-A3B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.9 | 45.3 |
| Released | 2025-04-28 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 41K | 1M |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.12 | $0.40 |
| Output $ / M tokens | $0.50 | $1.60 |
| Results tracked | 32 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen3-30B-A3B: 37.5 (#194), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| SciCode | 33.3% | 45.5% |
| LMArena Coding | 1416 | 1473 |
| FrontierCode | — | 10.2% |
| WeirdML | 29.8% | — |
Agentic & Tool Use Qwen3-30B-A3B leads
Qwen3-30B-A3B: 29.8 (#82), Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Qwen3-30B-A3B: 22.2 (#204), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| CritPt | 0.3% | 9.1% |
| Chess Puzzles | 8% | 24% |
| LMArena Hard Prompts | 1398 | 1460 |
| DTBench | 69.3% | 84% |
| LMCA | 22.4% | 37.6% |
| Epoch Capabilities Index | 139.63 | 147.37 |
| Kagi LLM Benchmark | 54.9% | — |
| NYT Connections (extended) | — | 74.8% |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.7 Plus leads
Qwen3-30B-A3B: 37.4 (#157), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 70.3% | 93.3% |
| LMArena Math | 1394 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| MathArena Final-Answer Competitions | 47.8% | — |
Knowledge Qwen3.7 Plus leads
Qwen3-30B-A3B: 41.8 (#105), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 70.1% | 87.9% |
| LMArena Expert | 1396 | 1467 |
| Confabulations | 12.3% | — |
Multimodal Not comparable
Qwen3-30B-A3B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
Qwen3-30B-A3B: 49.5 (#132), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1372 | 1445 |
| LMArena Chinese | 1433 | 1510 |
| LMArena French | 1418 | 1473 |
| LMArena German | 1380 | 1471 |
| LMArena Japanese | 1337 | 1413 |
| LMArena Korean | 1331 | 1415 |
| LMArena Russian | 1370 | 1457 |
| LMArena Spanish | 1404 | 1457 |
Instruction Following Qwen3.7 Plus leads
Qwen3-30B-A3B: 72.0 (#142), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1363 | 1440 |
Long Context Qwen3.7 Plus leads
Qwen3-30B-A3B: 31.0 (#283), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1379 | 1455 |
| Fiction.LiveBench | 40.6% | — |
Writing & Preference Qwen3.7 Plus leads
Qwen3-30B-A3B: 55.6 (#143), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Qwen3-30B-A3B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1384 | 1455 |
| LMArena Creative Writing | 1317 | 1439 |
| LMArena Multi-Turn | 1378 | 1460 |
| Short-Story Creative Writing | 75.3% | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 3.3× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, Qwen3-30B-A3B or Qwen3.7 Plus?
Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is Qwen3-30B-A3B or Qwen3.7 Plus better for coding?
They score almost the same on coding (37.5 vs 36.6); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 41K.
How many benchmarks do Qwen3-30B-A3B and Qwen3.7 Plus share?
25 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Qwen3.7 Plus has 32.