Model comparison
Qwen-14B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 0 categories and Step 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 58.8 to 27.6.
Side by side
| Qwen-14B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.4 | 42.3 |
| Released | 2023-09-24 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 18 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen-14B: 31.2 (#288), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1071 | 1436 |
Reasoning Step 3.5 Flash leads
Qwen-14B: 19.6 (#257), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Step 3.5 Flash leads
Qwen-14B: 31.2 (#227), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1068 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Step 3.5 Flash: 39.6 (#132)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | — | 1421 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Step 3.5 Flash leads
Qwen-14B: 27.5 (#275), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1041 | 1385 |
| LMArena Chinese | 1077 | 1447 |
| LMArena French | — | 1421 |
| LMArena German | — | 1405 |
| LMArena Japanese | — | 1354 |
| LMArena Korean | — | 1352 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Step 3.5 Flash leads
Qwen-14B: 52.4 (#289), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1031 | 1385 |
Long Context Step 3.5 Flash leads
Qwen-14B: 31.3 (#280), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1028 | 1402 |
Writing & Preference Step 3.5 Flash leads
Qwen-14B: 27.6 (#299), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Qwen-14B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1051 | 1403 |
| LMArena Creative Writing | 1028 | 1357 |
| LMArena Multi-Turn | 1022 | 1405 |
Frequently asked questions
Is Qwen-14B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 31.4 on the Noometry Index.
Is Qwen-14B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Step 3.5 Flash share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Step 3.5 Flash has 19.