Model comparison
Qwen3 14B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 35.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in coding, where Step 3.5 Flash leads 41.7 to 36.7.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
- Step 3.5 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Qwen3 14B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 35.0 | 41.7 |
| Released | 2025-04 | 2026-01-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 8K | 256K |
| Input $ / M tokens | $0.35 | $0.10 |
| Output $ / M tokens | $1.40 | $0.30 |
| Results tracked | 12 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen3 14B: 36.7 (#191), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| SciCode | 31.6% | — |
| LMArena Coding | — | 1436 |
Agentic & Tool Use Not comparable
Qwen3 14B: 29.4 (#78), Step 3.5 Flash: —
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | — |
Reasoning Step 3.5 Flash leads
Qwen3 14B: 18.1 (#272), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | — |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 0% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1411 |
| DTBench | 64% | — |
| LMCA | 18.2% | — |
| Epoch Capabilities Index | 138.23 | — |
Math Step 3.5 Flash leads
Qwen3 14B: 37.0 (#102), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LMArena Math | — | 1408 |
Knowledge Too close to call
Qwen3 14B: 39.2 (#124), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| GPQA Diamond | 63.8% | — |
| Vectara Hallucination Rate | 5.4% | — |
| LMArena Expert | — | 1422 |
Multilingual Not comparable
Qwen3 14B: —, Step 3.5 Flash: 50.7 (#115)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1386 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
Qwen3 14B: —, Step 3.5 Flash: 73.3 (#119)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context Step 3.5 Flash leads
Qwen3 14B: 38.0 (#201), Step 3.5 Flash: 42.8 (#112)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
| LMArena Longer Query | — | 1402 |
Writing & Preference Not comparable
Qwen3 14B: —, Step 3.5 Flash: 59.0 (#108)
| Benchmark | Qwen3 14B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is Qwen3 14B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 35.0 on the Noometry Index.
Which is cheaper, Qwen3 14B 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 14B lists at $0.35 and $1.40.
Is Qwen3 14B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 36.7 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 131K.
How many benchmarks do Qwen3 14B and Step 3.5 Flash share?
0 benchmarks have published results for both models. Qwen3 14B has 12 scored results on Noometry and Step 3.5 Flash has 19.