Model comparison
Qwen3 Max vs Step 3
Qwen3 Max is the stronger model overall, scoring 43.7 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 16 benchmarks with published results for both. Qwen3 Max scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 36.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 72.5% for Qwen3 Max and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen3 Max | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 43.7 | 40.5 |
| Released | 2025-09-23 | — |
| Weights | Proprietary | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.20 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 33 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
Qwen3 Max: 43.0 (#93), Step 3: 40.1 (#147)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Coding | 1456 | 1367 |
| ALE-Bench | 370.45 | — |
Agentic & Tool Use Not comparable
Qwen3 Max: —, Step 3: —
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| Vending-Bench 2 | 71.56 | — |
Reasoning Step 3 leads
Qwen3 Max: 22.6 (#190), Step 3: 28.4 (#105)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 72.5% | 62.3% |
| LMArena Hard Prompts | 1448 | 1355 |
| NYT Connections (extended) | 30.1% | — |
| Chess Puzzles | 4% | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 82.1% | — |
| LMCA | 28.3% | — |
| Epoch Capabilities Index | 142.38 | — |
Math Qwen3 Max leads
Qwen3 Max: 38.7 (#131), Step 3: 37.6 (#148)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Math | 1446 | 1366 |
| FrontierMath (Tiers 1-3) | 18.9% | — |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| MATH Level 5 | 97.1% | — |
Knowledge Qwen3 Max leads
Qwen3 Max: 48.1 (#78), Step 3: 36.8 (#164)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Expert | 1455 | 1333 |
| GPQA Diamond | 72.6% | — |
| SimpleQA Verified | 48.7% | — |
Multimodal Not comparable
Qwen3 Max: —, Step 3: 35.5 (#86)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Qwen3 Max leads
Qwen3 Max: 53.7 (#62), Step 3: 46.3 (#159)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Non-English | 1429 | 1327 |
| LMArena Chinese | 1478 | 1397 |
| LMArena German | 1463 | 1371 |
| LMArena Korean | 1399 | 1269 |
| LMArena Russian | 1428 | 1331 |
| LMArena Spanish | 1462 | 1371 |
| LMArena French | 1449 | — |
| LMArena Japanese | 1397 | — |
Instruction Following Qwen3 Max leads
Qwen3 Max: 74.8 (#87), Step 3: 70.4 (#164)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1419 | 1332 |
Long Context Qwen3 Max leads
Qwen3 Max: 41.6 (#134), Step 3: 40.3 (#157)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Longer Query | 1438 | 1326 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 14.5% | — |
Writing & Preference Qwen3 Max leads
Qwen3 Max: 62.4 (#76), Step 3: 54.3 (#151)
| Benchmark | Qwen3 Max | Step 3 |
|---|---|---|
| LMArena Text | 1439 | 1350 |
| LMArena Creative Writing | 1402 | 1321 |
| LMArena Multi-Turn | 1446 | 1341 |
Frequently asked questions
Is Qwen3 Max better than Step 3?
Qwen3 Max is the stronger model overall, scoring 43.7 to 40.5 on the Noometry Index.
Is Qwen3 Max or Step 3 better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 40.1 in the Noometry coding category.
How many benchmarks do Qwen3 Max and Step 3 share?
16 benchmarks have published results for both models. Qwen3 Max has 33 scored results on Noometry and Step 3 has 17.