Model comparison
Qwen3-Next 80B-A3B Instruct vs Step 3.7 Flash
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.1× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- The widest gap is in reasoning, where Qwen3-Next 80B-A3B Instruct leads 31.1 to 21.6.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
- Step 3.7 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 43.0 | 37.3 |
| Released | 2025-09 | 2026-05-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 33K | 256K |
| Input $ / M tokens | $0.50 | $0.18 |
| Output $ / M tokens | $2 | $1.11 |
| Results tracked | 25 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
Qwen3-Next 80B-A3B Instruct: 42.5 (#98), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| LMArena Coding | 1440 | — |
| ALE-Bench | — | 694.12 |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Qwen3-Next 80B-A3B Instruct: 31.1 (#81), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| Kagi LLM Benchmark | 66.7% | — |
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1428 | — |
Math Step 3.7 Flash leads
Qwen3-Next 80B-A3B Instruct: 38.8 (#126), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| Omni-MATH | 46.7% | — |
| LMArena Math | 1440 | — |
Knowledge Not comparable
Qwen3-Next 80B-A3B Instruct: 41.8 (#106), Step 3.7 Flash: —
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| MMLU-Pro | 78.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 63% | — |
| LMArena Expert | 1417 | — |
Multilingual Not comparable
Qwen3-Next 80B-A3B Instruct: 52.1 (#93), Step 3.7 Flash: —
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Chinese | 1460 | — |
| LMArena French | 1413 | — |
| LMArena German | 1417 | — |
| LMArena Japanese | 1395 | — |
| LMArena Korean | 1364 | — |
| LMArena Russian | 1404 | — |
| LMArena Spanish | 1435 | — |
Instruction Following Not comparable
Qwen3-Next 80B-A3B Instruct: 70.8 (#159), Step 3.7 Flash: —
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| IFEval | 81% | — |
| LMArena Instruction Following | 1389 | — |
Long Context Not comparable
Qwen3-Next 80B-A3B Instruct: 37.0 (#223), Step 3.7 Flash: —
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 55.6% | — |
| LMArena Longer Query | 1403 | — |
Writing & Preference Not comparable
Qwen3-Next 80B-A3B Instruct: 58.0 (#121), Step 3.7 Flash: —
| Benchmark | Qwen3-Next 80B-A3B Instruct | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1334 | — |
| WildBench | 80.7% | — |
| LMArena Multi-Turn | 1416 | — |
Frequently asked questions
Is Qwen3-Next 80B-A3B Instruct better than Step 3.7 Flash?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.1× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Which is cheaper, Qwen3-Next 80B-A3B Instruct or Step 3.7 Flash?
Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is Qwen3-Next 80B-A3B Instruct or Step 3.7 Flash better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 131K.
How many benchmarks do Qwen3-Next 80B-A3B Instruct and Step 3.7 Flash share?
0 benchmarks have published results for both models. Qwen3-Next 80B-A3B Instruct has 25 scored results on Noometry and Step 3.7 Flash has 5.