Model comparison
Qwen3.7 Plus vs Step 3
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 39.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 16 benchmarks with published results for both. Qwen3.7 Plus scores higher in 8 categories and Step 3 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 36.2.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen3.7 Plus | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 45.0 | 39.9 |
| Released | 2026-06-02 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $1.60 | — |
| Results tracked | 32 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3.7 Plus: 36.1 (#200), Step 3: 39.5 (#144)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Coding | 1473 | 1367 |
| FrontierCode | 10.2% | — |
| SciCode | 45.5% | — |
Agentic & Tool Use Not comparable
Qwen3.7 Plus: 21.2 (#130), Step 3: —
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| OSWorld 2.0 | 2.8% | — |
Reasoning Qwen3.7 Plus leads
Qwen3.7 Plus: 38.4 (#54), Step 3: 27.6 (#102)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1460 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 74.8% | — |
| CritPt | 9.1% | — |
| Chess Puzzles | 24% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 84% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 147.39 | — |
Math Qwen3.7 Plus leads
Qwen3.7 Plus: 49.3 (#47), Step 3: 34.9 (#148)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Math | 1467 | 1366 |
| FrontierMath (Tiers 1-3) | 34.4% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
Knowledge Qwen3.7 Plus leads
Qwen3.7 Plus: 54.9 (#46), Step 3: 36.2 (#161)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Expert | 1467 | 1333 |
| GPQA Diamond | 87.9% | — |
Multimodal Qwen3.7 Plus leads
Qwen3.7 Plus: 41.2 (#30), Step 3: 34.9 (#81)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Vision | 1281 | 1176 |
| LMArena Document | 1444 | — |
Multilingual Qwen3.7 Plus leads
Qwen3.7 Plus: 55.0 (#36), Step 3: 46.5 (#154)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Non-English | 1445 | 1327 |
| LMArena Chinese | 1510 | 1396 |
| LMArena German | 1471 | 1371 |
| LMArena Korean | 1416 | 1271 |
| LMArena Russian | 1457 | 1331 |
| LMArena Spanish | 1453 | 1372 |
| LMArena French | 1471 | — |
| LMArena Japanese | 1411 | — |
Instruction Following Qwen3.7 Plus leads
Qwen3.7 Plus: 75.9 (#49), Step 3: 70.6 (#159)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1439 | 1332 |
Long Context Qwen3.7 Plus leads
Qwen3.7 Plus: 44.5 (#61), Step 3: 40.3 (#152)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Longer Query | 1454 | 1326 |
Writing & Preference Qwen3.7 Plus leads
Qwen3.7 Plus: 64.5 (#54), Step 3: 54.5 (#146)
| Benchmark | Qwen3.7 Plus | Step 3 |
|---|---|---|
| LMArena Text | 1454 | 1351 |
| LMArena Creative Writing | 1439 | 1322 |
| LMArena Multi-Turn | 1459 | 1340 |
Frequently asked questions
Is Qwen3.7 Plus better than Step 3?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 39.9 on the Noometry Index.
Is Qwen3.7 Plus or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 36.1 in the Noometry coding category.
How many benchmarks do Qwen3.7 Plus and Step 3 share?
16 benchmarks have published results for both models. Qwen3.7 Plus has 32 scored results on Noometry and Step 3 has 17.