Model comparison
Qwen3-Next 80B-A3B Instruct vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.0 on the Noometry Index. Qwen3-Next 80B-A3B Instruct costs 1.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 13 benchmarks with published results for both. Qwen3-Next 80B-A3B Instruct scores higher in 1 category and Step 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 42.5.
- Qwen3-Next 80B-A3B Instruct is cheaper at $0.50 / $2 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 131K.
- Qwen3-Next 80B-A3B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen3-Next 80B-A3B Instruct | Step 5 Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 43.0 | 47.9 |
| Released | 2025-09 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.02M |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.50 | $1 |
| Output $ / M tokens | $2 | $2.70 |
| Results tracked | 25 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 42.5 (#98), Step 5 Preview: 51.8 (#36)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1440 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 31.1 (#81), Step 5 Preview: 40.0 (#57)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1465 |
| Kagi LLM Benchmark | 66.7% | — |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 38.8 (#126), Step 5 Preview: 46.1 (#72)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Math | 1440 | 1470 |
| ProofBench | — | 42% |
| Omni-MATH | 46.7% | — |
Knowledge Too close to call
Qwen3-Next 80B-A3B Instruct: 41.8 (#106), Step 5 Preview: 41.2 (#112)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1417 | 1470 |
| MMLU-Pro | 78.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 63% | — |
Multimodal Not comparable
Qwen3-Next 80B-A3B Instruct: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 52.1 (#93), Step 5 Preview: 53.8 (#54)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1407 | 1432 |
| LMArena Chinese | 1460 | 1519 |
| LMArena Russian | 1404 | 1436 |
| LMArena Spanish | 1435 | 1439 |
| LMArena French | 1413 | — |
| LMArena German | 1417 | — |
| LMArena Japanese | 1395 | — |
| LMArena Korean | 1364 | — |
Instruction Following Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 70.8 (#159), Step 5 Preview: 76.0 (#50)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1389 | 1444 |
| IFEval | 81% | — |
Long Context Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 37.0 (#223), Step 5 Preview: 44.5 (#64)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1403 | 1455 |
| Fiction.LiveBench | 55.6% | — |
Writing & Preference Step 5 Preview leads
Qwen3-Next 80B-A3B Instruct: 58.0 (#121), Step 5 Preview: 62.8 (#71)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 5 Preview |
|---|---|---|
| LMArena Text | 1417 | 1442 |
| LMArena Creative Writing | 1334 | 1410 |
| LMArena Multi-Turn | 1416 | 1447 |
| WildBench | 80.7% | — |
Frequently asked questions
Is Qwen3-Next 80B-A3B Instruct better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.0 on the Noometry Index. Qwen3-Next 80B-A3B Instruct costs 1.6× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3-Next 80B-A3B Instruct or Step 5 Preview?
Qwen3-Next 80B-A3B Instruct is cheaper. It lists at $0.50 per million input tokens and $2 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is Qwen3-Next 80B-A3B Instruct or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.5 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 Qwen3-Next 80B-A3B Instruct and Step 5 Preview share?
13 benchmarks have published results for both models. Qwen3-Next 80B-A3B Instruct has 25 scored results on Noometry and Step 5 Preview has 18.