Model comparison
Qwen2.5-Max vs Step 3
Qwen2.5-Max and Step 3 score almost the same on the Noometry Index (40.7 vs 40.5), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. Qwen2.5-Max scores higher in 5 categories and Step 3 in 3 categories; 6 gaps are clear of the uncertainty.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5-Max | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 40.7 | 40.5 |
| Released | 2025-01-25 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Qwen2.5-Max: 41.8 (#117), Step 3: 40.1 (#147)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Coding | 1359 | 1367 |
| LiveBench Coding | 64.4% | — |
Reasoning Step 3 leads
Qwen2.5-Max: 25.6 (#147), Step 3: 28.4 (#105)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1360 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 51.4% | — |
| LiveBench Data Analysis | 67.9% | — |
| Epoch Capabilities Index | 132.53 | — |
| LiveBench | 62.3% | — |
Math Too close to call
Qwen2.5-Max: 36.9 (#162), Step 3: 37.6 (#148)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Math | 1369 | 1366 |
| LiveBench Math | 58.4% | — |
Knowledge Step 3 leads
Qwen2.5-Max: 35.3 (#186), Step 3: 36.8 (#164)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Expert | 1337 | 1333 |
| Confabulations | 21.8% | — |
Multimodal Not comparable
Qwen2.5-Max: —, Step 3: 35.5 (#86)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Qwen2.5-Max leads
Qwen2.5-Max: 48.1 (#146), Step 3: 46.3 (#159)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Non-English | 1352 | 1327 |
| LMArena Chinese | 1382 | 1397 |
| LMArena German | 1350 | 1371 |
| LMArena Korean | 1304 | 1269 |
| LMArena Russian | 1353 | 1331 |
| LMArena Spanish | 1377 | 1371 |
| LMArena French | 1396 | — |
| LMArena Japanese | 1300 | — |
Instruction Following Too close to call
Qwen2.5-Max: 71.3 (#152), Step 3: 70.4 (#164)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1335 | 1332 |
| LiveBench Instruction Following | 75.3% | — |
Long Context Qwen2.5-Max leads
Qwen2.5-Max: 41.4 (#142), Step 3: 40.3 (#157)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Longer Query | 1358 | 1326 |
Writing & Preference Qwen2.5-Max leads
Qwen2.5-Max: 55.4 (#146), Step 3: 54.3 (#151)
| Benchmark | Qwen2.5-Max | Step 3 |
|---|---|---|
| LMArena Text | 1367 | 1350 |
| LMArena Creative Writing | 1339 | 1321 |
| LMArena Multi-Turn | 1364 | 1341 |
| Short-Story Creative Writing | 72.9% | — |
| LiveBench Language | 56.3% | — |
Frequently asked questions
Is Qwen2.5-Max better than Step 3?
Qwen2.5-Max and Step 3 score almost the same on the Noometry Index (40.7 vs 40.5), so choose on price, context window or the category you care about most.
Is Qwen2.5-Max or Step 3 better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 40.1 in the Noometry coding category.
How many benchmarks do Qwen2.5-Max and Step 3 share?
15 benchmarks have published results for both models. Qwen2.5-Max has 27 scored results on Noometry and Step 3 has 17.