Model comparison
Qwen3 235B-A22B vs Step 3
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 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 235B-A22B scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 34.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 69.4% for Qwen3 235B-A22B and 62.3% for Step 3.
Side by side
| Qwen3 235B-A22B | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 43.2 | 39.9 |
| Released | 2025-04 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 49 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 43.8 (#72), Step 3: 39.5 (#144)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Coding | 1445 | 1367 |
| Aider Polyglot | 59.6% | — |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.7 (#48), Step 3: —
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |
Reasoning Step 3 leads
Qwen3 235B-A22B: 15.8 (#302), Step 3: 27.6 (#102)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 62.3% |
| LMArena Hard Prompts | 1433 | 1355 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 29.3% | — |
| Epoch Capabilities Index | 143.87 | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 48.5 (#51), Step 3: 34.9 (#148)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Math | 1431 | 1366 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3 235B-A22B leads
Qwen3 235B-A22B: 49.5 (#67), Step 3: 36.2 (#161)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Expert | 1460 | 1333 |
| GPQA Diamond | 80.1% | — |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
Multimodal Not comparable
Qwen3 235B-A22B: —, Step 3: 34.9 (#81)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Qwen3 235B-A22B leads
Qwen3 235B-A22B: 52.5 (#84), Step 3: 46.5 (#154)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Non-English | 1410 | 1327 |
| LMArena Chinese | 1481 | 1396 |
| LMArena German | 1432 | 1371 |
| LMArena Korean | 1391 | 1271 |
| LMArena Russian | 1411 | 1331 |
| LMArena Spanish | 1429 | 1372 |
| LMArena French | 1445 | — |
| LMArena Japanese | 1400 | — |
Instruction Following Qwen3 235B-A22B leads
Qwen3 235B-A22B: 72.8 (#132), Step 3: 70.6 (#159)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1408 | 1332 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#25), Step 3: 40.3 (#152)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1426 | 1326 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3 235B-A22B leads
Qwen3 235B-A22B: 59.8 (#103), Step 3: 54.5 (#146)
| Benchmark | Qwen3 235B-A22B | Step 3 |
|---|---|---|
| LMArena Text | 1419 | 1351 |
| LMArena Creative Writing | 1384 | 1322 |
| LMArena Multi-Turn | 1432 | 1340 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Step 3?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 39.9 on the Noometry Index.
Is Qwen3 235B-A22B or Step 3 better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 39.5 in the Noometry coding category.
How many benchmarks do Qwen3 235B-A22B and Step 3 share?
16 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Step 3 has 17.