Model comparison
Qwen3.5 122B-A10B vs Step 3
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 16 benchmarks with published results for both. Qwen3.5 122B-A10B scores higher in 7 categories and Step 3 in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.0 to 54.3.
Side by side
| Qwen3.5 122B-A10B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 42.1 | 40.5 |
| Released | 2026-02-23 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen3.5 122B-A10B: 39.1 (#162), Step 3: 40.1 (#147)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Coding | 1436 | 1367 |
| LMArena WebDev | 1360 | — |
| SciCode | 35.6% | — |
Reasoning Step 3 leads
Qwen3.5 122B-A10B: 27.2 (#123), Step 3: 28.4 (#105)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1421 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 51.7% | — |
| CritPt | 0.9% | — |
| Thematic Generalization | 51.2% | — |
| Mystery Game Puzzles | 17% | — |
| DTBench | 84.3% | — |
| LMCA | 32.2% | — |
Math Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 39.1 (#112), Step 3: 37.6 (#148)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Math | 1432 | 1366 |
Knowledge Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 38.8 (#142), Step 3: 36.8 (#164)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Expert | 1432 | 1333 |
| Vectara Hallucination Rate | 11.2% | — |
Multimodal Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 39.6 (#57), Step 3: 35.5 (#86)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Vision | 1245 | 1177 |
Multilingual Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 51.6 (#107), Step 3: 46.3 (#159)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Non-English | 1400 | 1327 |
| LMArena Chinese | 1462 | 1397 |
| LMArena German | 1426 | 1371 |
| LMArena Korean | 1352 | 1269 |
| LMArena Russian | 1400 | 1331 |
| LMArena Spanish | 1424 | 1371 |
| LMArena French | 1442 | — |
| LMArena Japanese | 1367 | — |
Instruction Following Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 73.8 (#115), Step 3: 70.4 (#164)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1332 |
Long Context Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 43.0 (#109), Step 3: 40.3 (#157)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1410 | 1326 |
Writing & Preference Qwen3.5 122B-A10B leads
Qwen3.5 122B-A10B: 60.0 (#105), Step 3: 54.3 (#151)
| Benchmark | Qwen3.5 122B-A10B | Step 3 |
|---|---|---|
| LMArena Text | 1417 | 1350 |
| LMArena Creative Writing | 1368 | 1321 |
| LMArena Multi-Turn | 1416 | 1341 |
Frequently asked questions
Is Qwen3.5 122B-A10B better than Step 3?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 40.5 on the Noometry Index.
Is Qwen3.5 122B-A10B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 39.1 in the Noometry coding category.
How many benchmarks do Qwen3.5 122B-A10B and Step 3 share?
16 benchmarks have published results for both models. Qwen3.5 122B-A10B has 27 scored results on Noometry and Step 3 has 17.