Model comparison
Qwen2.5 72B Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 19.3.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 72B Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.9 | 47.9 |
| Released | 2024-09 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $1.40 | $1 |
| Output $ / M tokens | $5.60 | $2.70 |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen2.5 72B Instruct: 33.2 (#260), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1292 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.1 (#133), Step 5 Preview: —
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Step 5 Preview leads
Qwen2.5 72B Instruct: 22.3 (#199), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1465 |
| CritPt | — | 20.9% |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Step 5 Preview leads
Qwen2.5 72B Instruct: 19.3 (#287), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1283 | 1470 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| ProofBench | — | 42% |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Step 5 Preview leads
Qwen2.5 72B Instruct: 27.0 (#253), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1245 | 1470 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multimodal Not comparable
Qwen2.5 72B Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen2.5 72B Instruct: 41.0 (#213), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1252 | 1432 |
| LMArena Chinese | 1272 | 1519 |
| LMArena Russian | 1264 | 1436 |
| LMArena Spanish | 1256 | 1439 |
| LMArena French | 1280 | — |
| LMArena German | 1234 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |
Instruction Following Step 5 Preview leads
Qwen2.5 72B Instruct: 65.5 (#221), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1254 | 1444 |
| IFEval | 80.6% | — |
Long Context Step 5 Preview leads
Qwen2.5 72B Instruct: 38.9 (#188), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1282 | 1455 |
Writing & Preference Step 5 Preview leads
Qwen2.5 72B Instruct: 46.7 (#215), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen2.5 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1269 | 1442 |
| LMArena Creative Writing | 1221 | 1410 |
| LMArena Multi-Turn | 1272 | 1447 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 31.9 on the Noometry Index.
Which is cheaper, Qwen2.5 72B Instruct or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Qwen2.5 72B Instruct or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.2 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 72B Instruct and Step 5 Preview share?
13 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Step 5 Preview has 18.