Model comparison
Qwen3-1.7B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 26.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 18.5.
- Qwen3-1.7B has downloadable open weights; the other is API-only.
Side by side
| Qwen3-1.7B | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 26.2 | 43.8 |
| Released | 2025-04-29 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 4 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen3-1.7B: —, Step 5 Preview: 50.6 (#40)
| Benchmark | Qwen3-1.7B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
Agentic & Tool Use Not comparable
Qwen3-1.7B: 24.5 (#108), Step 5 Preview: —
| Benchmark | Qwen3-1.7B | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.4% | — |
Reasoning Step 5 Preview leads
Qwen3-1.7B: 18.5 (#263), Step 5 Preview: 38.0 (#58)
| Benchmark | Qwen3-1.7B | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
Math Not comparable
Qwen3-1.7B: 15.4 (#288), Step 5 Preview: —
| Benchmark | Qwen3-1.7B | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | — |
Knowledge Not comparable
Qwen3-1.7B: 19.6 (#273), Step 5 Preview: —
| Benchmark | Qwen3-1.7B | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 38% | — |
Frequently asked questions
Is Qwen3-1.7B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 26.2 on the Noometry Index.
How many benchmarks do Qwen3-1.7B and Step 5 Preview share?
0 benchmarks have published results for both models. Qwen3-1.7B has 4 scored results on Noometry and Step 5 Preview has 3.