Model comparison
Qwen3 235B-A22B vs Step 3.7 Flash
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.9× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 2 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 2 categories and Step 3.7 Flash in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 42.9.
- Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $0.70 / $2.80 for Qwen3 235B-A22B.
- Step 3.7 Flash accepts more context: 256K tokens versus 131K.
Side by side
| Qwen3 235B-A22B | Step 3.7 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 43.5 | 37.3 |
| Released | 2025-04 | 2026-05-29 |
| Weights | Open | Open |
| Context window | 131K | 256K |
| Max output | 16K | 256K |
| Input $ / M tokens | $0.70 | $0.18 |
| Output $ / M tokens | $2.80 | $1.11 |
| Results tracked | 49 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 44.3 (#75), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| SciCode | 42.4% | 40% |
| Aider Polyglot | 59.6% | — |
| WeirdML | 41% | — |
| LMArena Coding | 1445 | — |
| ALE-Bench | — | 694.12 |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 52.1% | — |
| Vending-Bench 2 | -11.34 | — |
Reasoning Step 3.7 Flash leads
Qwen3 235B-A22B: 15.7 (#311), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| CritPt | 0% | 2.3% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 39.7% |
| ARC-AGI-1 | 11% | — |
| Chess Puzzles | 12% | — |
| LMArena Hard Prompts | 1433 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 29.3% | — |
| Epoch Capabilities Index | 143.85 | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| Omni-MATH | 71.8% | — |
| LMArena Math | 1432 | — |
| MATH Level 5 | 68.9% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Not comparable
Qwen3 235B-A22B: 49.6 (#73), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 80.1% | — |
| SimpleQA Verified | 40.4% | — |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
| LMArena Expert | 1463 | — |
Multilingual Not comparable
Qwen3 235B-A22B: 52.3 (#89), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1481 | — |
| LMArena French | 1445 | — |
| LMArena German | 1433 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1391 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1430 | — |
Instruction Following Not comparable
Qwen3 235B-A22B: 72.6 (#136), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| IFEval | 83.5% | — |
| LMArena Instruction Following | 1408 | — |
Long Context Not comparable
Qwen3 235B-A22B: 46.1 (#26), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 75% | — |
| LMArena Longer Query | 1426 | — |
Writing & Preference Not comparable
Qwen3 235B-A22B: 59.6 (#108), Step 3.7 Flash: —
| Benchmark | Qwen3 235B-A22B | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1419 | — |
| LMArena Creative Writing | 1384 | — |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
| LMArena Multi-Turn | 1432 | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Step 3.7 Flash?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 37.3 on the Noometry Index. Step 3.7 Flash costs 2.9× less per token, which makes it the better buy when Qwen3 235B-A22B's lead doesn't matter for your workload.
Which is cheaper, Qwen3 235B-A22B or Step 3.7 Flash?
Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Qwen3 235B-A22B lists at $0.70 and $2.80.
Is Qwen3 235B-A22B or Step 3.7 Flash better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 40.0 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 131K.
How many benchmarks do Qwen3 235B-A22B and Step 3.7 Flash share?
2 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Step 3.7 Flash has 5.