Model comparison
Qwen-14B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 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 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 27.6.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Qwen-14B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.4 | 47.9 |
| Released | 2023-09-24 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen-14B: 31.2 (#288), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1071 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Qwen-14B: 19.6 (#257), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1465 |
| CritPt | — | 20.9% |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Step 5 Preview leads
Qwen-14B: 31.2 (#227), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1068 | 1470 |
| ProofBench | — | 42% |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multimodal Not comparable
Qwen-14B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen-14B: 27.5 (#275), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1041 | 1432 |
| LMArena Chinese | 1077 | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Qwen-14B: 52.4 (#289), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1031 | 1444 |
Long Context Step 5 Preview leads
Qwen-14B: 31.3 (#280), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1028 | 1455 |
Writing & Preference Step 5 Preview leads
Qwen-14B: 27.6 (#299), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen-14B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1051 | 1442 |
| LMArena Creative Writing | 1028 | 1410 |
| LMArena Multi-Turn | 1022 | 1447 |
Frequently asked questions
Is Qwen-14B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.4 on the Noometry Index.
Is Qwen-14B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 31.2 in the Noometry coding category.
How many benchmarks do Qwen-14B and Step 5 Preview share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Step 5 Preview has 18.