Model comparison
Qwen3 14B vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 35.0 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 1 benchmark with published results for both. Qwen3 14B scores higher in 2 categories and Step 3 in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 27.6 to 18.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 49.1% for Qwen3 14B and 62.3% for Step 3.
Side by side
| Qwen3 14B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 35.0 | 39.9 |
| Released | 2025-04 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $1.40 | — |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3 14B: 36.7 (#191), Step 3: 39.5 (#144)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| SciCode | 31.6% | — |
| LMArena Coding | — | 1367 |
Agentic & Tool Use Not comparable
Qwen3 14B: 29.4 (#78), Step 3: —
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 41% | — |
Reasoning Step 3 leads
Qwen3 14B: 18.1 (#272), Step 3: 27.6 (#102)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 49.1% | 62.3% |
| CritPt | 0% | — |
| Chess Puzzles | 4% | — |
| LMArena Hard Prompts | — | 1355 |
| DTBench | 64% | — |
| LMCA | 18.2% | — |
| Epoch Capabilities Index | 138.23 | — |
Math Qwen3 14B leads
Qwen3 14B: 37.0 (#102), Step 3: 34.9 (#148)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| LMArena Math | — | 1366 |
Knowledge Qwen3 14B leads
Qwen3 14B: 39.2 (#124), Step 3: 36.2 (#161)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| GPQA Diamond | 63.8% | — |
| Vectara Hallucination Rate | 5.4% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Qwen3 14B: —, Step 3: 34.9 (#81)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Qwen3 14B: —, Step 3: 46.5 (#154)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
Qwen3 14B: —, Step 3: 70.6 (#159)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Step 3 leads
Qwen3 14B: 38.0 (#201), Step 3: 40.3 (#152)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| Fiction.LiveBench | 62.5% | — |
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Qwen3 14B: —, Step 3: 54.5 (#146)
| Benchmark | Qwen3 14B | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Qwen3 14B better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 35.0 on the Noometry Index.
Is Qwen3 14B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 36.7 in the Noometry coding category.
How many benchmarks do Qwen3 14B and Step 3 share?
1 benchmark has published results for both models. Qwen3 14B has 12 scored results on Noometry and Step 3 has 17.