Model comparison
Qwen2.5-VL 72B Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 1 benchmark with published results for both. Qwen2.5-VL 72B Instruct scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 20.7.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-VL 72B Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 29.9 | 47.9 |
| Released | 2024-09 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.02M |
| Max output | 8K | 66K |
| Input $ / M tokens | $2.80 | $1 |
| Output $ / M tokens | $8.40 | $2.70 |
| Results tracked | 6 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
Agentic & Tool Use Not comparable
Qwen2.5-VL 72B Instruct: 18.6 (#144), Step 5 Preview: —
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| OSWorld | 5% | — |
Reasoning Step 5 Preview leads
Qwen2.5-VL 72B Instruct: 20.7 (#233), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| Kagi LLM Benchmark | 36% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
Math Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
Knowledge Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
Multimodal Step 5 Preview leads
Qwen2.5-VL 72B Instruct: 33.5 (#97), Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1107 | 1267 |
| Video-MME | 73.5% | — |
| GeoBench | 62% | — |
| SpatialViz-Bench | 33.3% | — |
Multilingual Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
Qwen2.5-VL 72B Instruct: —, Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen2.5-VL 72B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is Qwen2.5-VL 72B Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 29.9 on the Noometry Index.
Which is cheaper, Qwen2.5-VL 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-VL 72B Instruct lists at $2.80 and $8.40.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 131K.
How many benchmarks do Qwen2.5-VL 72B Instruct and Step 5 Preview share?
1 benchmark has published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Step 5 Preview has 18.