Model comparison
Qwen2.5 7B Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 4.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in math, where Step 5 Preview leads 46.1 to 12.6.
- Qwen2.5 7B Instruct is cheaper at $0.17 / $0.70 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 7B Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 29.0 | 47.9 |
| Released | 2024-09 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.17 | $1 |
| Output $ / M tokens | $0.70 | $2.70 |
| Results tracked | 15 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen2.5 7B Instruct: 36.5 (#208), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1480 |
| BigCodeBench Complete | 46.1% | — |
Agentic & Tool Use Not comparable
Qwen2.5 7B Instruct: 23.8 (#124), Step 5 Preview: —
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| BALROG | 7.8% | — |
Reasoning Step 5 Preview leads
Qwen2.5 7B Instruct: 14.8 (#322), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1465 |
| DTBench | 47.7% | — |
| LMCA | 6.4% | — |
| Epoch Capabilities Index | 118.51 | — |
Math Step 5 Preview leads
Qwen2.5 7B Instruct: 12.6 (#306), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| ProofBench | — | 42% |
| Omni-MATH | 29.4% | — |
| LMArena Math | — | 1470 |
Knowledge Step 5 Preview leads
Qwen2.5 7B Instruct: 17.0 (#286), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 35.5% | — |
| MMLU-Pro | 53.9% | — |
| GPQA (HELM) | 34.1% | — |
| LMArena Expert | — | 1470 |
| MMLU | 72.9% | — |
Multimodal Not comparable
Qwen2.5 7B Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
Qwen2.5 7B Instruct: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Qwen2.5 7B Instruct: 63.2 (#231), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| IFEval | 74.1% | — |
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Qwen2.5 7B Instruct: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Step 5 Preview leads
Qwen2.5 7B Instruct: 48.8 (#195), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen2.5 7B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| WildBench | 73.1% | — |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Qwen2.5 7B Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.0 on the Noometry Index. Qwen2.5 7B Instruct costs 4.7× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen2.5 7B Instruct or Step 5 Preview?
Qwen2.5 7B Instruct is cheaper. It lists at $0.17 per million input tokens and $0.70 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Qwen2.5 7B Instruct or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 131K.
How many benchmarks do Qwen2.5 7B Instruct and Step 5 Preview share?
0 benchmarks have published results for both models. Qwen2.5 7B Instruct has 15 scored results on Noometry and Step 5 Preview has 18.