# Qwen3-30B-A3B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/qwen3-30b-a3b-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Qwen3-30B-A3B scores higher in 2 categories and Step 3.5 Flash in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where Step 3.5 Flash leads 42.8 to 31.0.
- The biggest single-benchmark swing is MathArena Final-Answer Competitions: 47.8% for Qwen3-30B-A3B and 66.8% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.12 / $0.50 for Qwen3-30B-A3B.
- Step 3.5 Flash accepts more context: 256K tokens versus 41K.

## Snapshot

| | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 38.5 | 41.7 |
| Rank | 174 | 116 |
| Context | 41K | 256K |
| Input $/M | $0.12 | $0.10 |
| Output $/M | $0.50 | $0.30 |
| Weights | Open | Open |

## Coding

- Qwen3-30B-A3B: 37.0 (#188)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1416 | 1436 |
| SciCode | 33.3% | — |
| WeirdML | 29.8% | — |

## Agentic & Tool Use

- Qwen3-30B-A3B: 29.5 (#75)
- Step 3.5 Flash: —

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41.4% | — |

## Reasoning

- Qwen3-30B-A3B: 21.6 (#193)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1398 | 1411 |
| Kagi LLM Benchmark | 54.9% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0.3% | — |
| Chess Puzzles | 8% | — |
| DTBench | 69.3% | — |
| LMCA | 22.4% | — |
| Epoch Capabilities Index | 139.63 | — |

## Math

- Qwen3-30B-A3B: 36.0 (#133)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 47.8% | 66.8% |
| LMArena Math | 1394 | 1408 |
| OTIS Mock AIME 2024-2025 | 70.3% | — |

## Knowledge

- Qwen3-30B-A3B: 41.7 (#96)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1395 | 1422 |
| GPQA Diamond | 70.1% | — |
| Confabulations | 12.3% | — |

## Multilingual

- Qwen3-30B-A3B: 49.8 (#126)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1372 | 1386 |
| LMArena Chinese | 1434 | 1448 |
| LMArena French | 1419 | 1421 |
| LMArena German | 1379 | 1404 |
| LMArena Japanese | 1338 | 1353 |
| LMArena Korean | 1333 | 1350 |
| LMArena Russian | 1369 | 1385 |
| LMArena Spanish | 1403 | 1419 |

## Instruction Following

- Qwen3-30B-A3B: 72.2 (#137)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1364 | 1385 |

## Long Context

- Qwen3-30B-A3B: 31.0 (#278)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1379 | 1402 |
| Fiction.LiveBench | 40.6% | — |

## Writing & Preference

- Qwen3-30B-A3B: 55.9 (#138)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Qwen3-30B-A3B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1384 | 1403 |
| LMArena Creative Writing | 1318 | 1357 |
| LMArena Multi-Turn | 1378 | 1405 |
| Short-Story Creative Writing | 75.3% | — |

## FAQ

### Is Qwen3-30B-A3B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 38.5 on the Noometry Index.

### Which is cheaper, Qwen3-30B-A3B or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Qwen3-30B-A3B lists at $0.12 and $0.50.

### Is Qwen3-30B-A3B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 37.0 in the Noometry coding category.

### Which has the bigger context window?

Step 3.5 Flash does, with 256K tokens against 41K.

### How many benchmarks do Qwen3-30B-A3B and Step 3.5 Flash share?

18 benchmarks have published results for both models. Qwen3-30B-A3B has 32 scored results on Noometry and Step 3.5 Flash has 19.