Model comparison
Qwen3-30B-A3B vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 38.9 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 2 categories and Qwen3.5-Flash in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 22.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 70.3% for Qwen3-30B-A3B and 84.4% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Qwen3.5-Flash 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 | Qwen3.5-Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.9 | 42.5 |
| Released | 2025-04-28 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 41K | 1M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.12 | $0.10 |
| Output $ / M tokens | $0.50 | $0.40 |
| Results tracked | 32 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-30B-A3B leads
Qwen3-30B-A3B: 37.5 (#194), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Coding | 1416 | 1412 |
| LMArena WebDev | — | 1244 |
| SciCode | 33.3% | — |
| WeirdML | 29.8% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Qwen3-30B-A3B: 29.8 (#82), Qwen3.5-Flash: —
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Qwen3-30B-A3B: 22.2 (#204), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 8% | 21% |
| LMArena Hard Prompts | 1398 | 1403 |
| DTBench | 69.3% | 82.9% |
| LMCA | 22.4% | 29.1% |
| Epoch Capabilities Index | 139.63 | 143.98 |
| Kagi LLM Benchmark | 54.9% | — |
| CritPt | 0.3% | — |
| Mystery Game Puzzles | — | 20% |
Math Too close to call
Qwen3-30B-A3B: 37.4 (#157), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 70.3% | 84.4% |
| LMArena Math | 1394 | 1407 |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| MathArena Final-Answer Competitions | 47.8% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Qwen3-30B-A3B: 41.8 (#105), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 70.1% | 82.3% |
| LMArena Expert | 1396 | 1407 |
| SimpleQA Verified | — | 20.3% |
| Confabulations | 12.3% | — |
| Vectara Hallucination Rate | — | 10.5% |
Multilingual Too close to call
Qwen3-30B-A3B: 49.5 (#132), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1372 | 1385 |
| LMArena Chinese | 1433 | 1446 |
| LMArena French | 1418 | 1412 |
| LMArena German | 1380 | 1390 |
| LMArena Japanese | 1337 | 1368 |
| LMArena Korean | 1331 | 1344 |
| LMArena Russian | 1370 | 1379 |
| LMArena Spanish | 1404 | 1400 |
Instruction Following Too close to call
Qwen3-30B-A3B: 72.0 (#142), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1363 | 1374 |
Long Context Qwen3.5-Flash leads
Qwen3-30B-A3B: 31.0 (#283), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1379 | 1392 |
| Fiction.LiveBench | 40.6% | — |
Writing & Preference Qwen3.5-Flash leads
Qwen3-30B-A3B: 55.6 (#143), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Qwen3-30B-A3B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1384 | 1397 |
| LMArena Creative Writing | 1317 | 1343 |
| LMArena Multi-Turn | 1378 | 1393 |
| Short-Story Creative Writing | 75.3% | — |
Frequently asked questions
Is Qwen3-30B-A3B better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 38.9 on the Noometry Index.
Which is cheaper, Qwen3-30B-A3B or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.
Is Qwen3-30B-A3B or Qwen3.5-Flash better for coding?
Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 41K.
How many benchmarks do Qwen3-30B-A3B and Qwen3.5-Flash share?
23 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Qwen3.5-Flash has 32.