Model comparison
Qwen1.5-14B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 32.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 14 benchmarks with published results for both. Qwen1.5-14B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 33.6.
Side by side
| Qwen1.5-14B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 32.7 | 40.5 |
| Released | 2024-02-04 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen1.5-14B: 33.1 (#263), Step 3: 40.1 (#147)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Coding | 1138 | 1367 |
Reasoning Step 3 leads
Qwen1.5-14B: 21.4 (#223), Step 3: 28.4 (#105)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Qwen1.5-14B: 32.4 (#215), Step 3: 37.6 (#148)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Math | 1125 | 1366 |
Knowledge Step 3 leads
Qwen1.5-14B: 29.8 (#232), Step 3: 36.8 (#164)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Expert | 1094 | 1333 |
| MMLU | 68.6% | — |
Multimodal Not comparable
Qwen1.5-14B: —, Step 3: 35.5 (#86)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Qwen1.5-14B: 30.7 (#262), Step 3: 46.3 (#159)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Non-English | 1095 | 1327 |
| LMArena Chinese | 1147 | 1397 |
| LMArena German | 1043 | 1371 |
| LMArena Russian | 1046 | 1331 |
| LMArena Spanish | 1085 | 1371 |
| LMArena French | 1116 | — |
| LMArena Japanese | 1019 | — |
| LMArena Korean | — | 1269 |
Instruction Following Step 3 leads
Qwen1.5-14B: 56.8 (#271), Step 3: 70.4 (#164)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1102 | 1332 |
Long Context Step 3 leads
Qwen1.5-14B: 33.7 (#257), Step 3: 40.3 (#157)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1113 | 1326 |
Writing & Preference Step 3 leads
Qwen1.5-14B: 33.6 (#276), Step 3: 54.3 (#151)
| Benchmark | Qwen1.5-14B | Step 3 |
|---|---|---|
| LMArena Text | 1128 | 1350 |
| LMArena Creative Writing | 1091 | 1321 |
| LMArena Multi-Turn | 1110 | 1341 |
Frequently asked questions
Is Qwen1.5-14B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 32.7 on the Noometry Index.
Is Qwen1.5-14B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.1 in the Noometry coding category.
How many benchmarks do Qwen1.5-14B and Step 3 share?
14 benchmarks have published results for both models. Qwen1.5-14B has 17 scored results on Noometry and Step 3 has 17.