Qwen3 235B A22B Thinking 2507 vs Step 5 Preview
Step 5 Preview leads Qwen3 235B A22B Thinking 2507 on the Artificial Analysis Intelligence Index, 43.7 to 12.7, and Step 5 Preview costs 1.3x less per output token ($2.70 vs $3.50 per million). Updated October 22, 2026; 25 benchmarks have a result for both.
Qwen3 235B A22B Thinking 2507 or Step 5 Preview: which to pick
Only Step 5 Preview has a coding score, 61.1 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding.
Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: medicine and healthcare or LMArena Text: Japanese, where it leads.
- Shared results
- 25
- Qwen3 235B A22B Thinking 2507 only
- 21
- Step 5 Preview only
- 36
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only Step 5 Preview has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Step 5 Preview
Step 5 Preview leads, 43.7 against 12.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3 235B A22B Thinking 2507 has a AA Agentic Index result, 1.3.
Directional only
Web design
Design Arena: websites
No call
Only Qwen3 235B A22B Thinking 2507 has a Design Arena: websites result, 1052.
Directional only
Long documents
Listed context window
Step 5 Preview
Step 5 Preview takes 1.05M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 $0.0022, Step 5 Preview $0.0024 per turn.
List prices
At a glance
- Coding index
- Qwen3 235B A22B Thinking 2507 not benchmarked, Step 5 Preview 61.1 from 4 benchmarks.
- Widest category
- Intelligence, 31.0 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: Qwen3 235B A22B Thinking 2507 12.7 against Step 5 Preview 43.7, 31.0 points apart on a 0 to 100 scale.
- Output price
- Qwen3 235B A22B Thinking 2507 $3.50 against Step 5 Preview $2.70 per million output tokens, 1.3x apart.
- Context window
- Qwen3 235B A22B Thinking 2507 takes 128K tokens, Step 5 Preview 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Qwen3 235B A22B Thinking 2507 | Bars | Step 5 Preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| General | 1 | 12 | ||
| All shared boards | 2 | 23 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 85.6% | Only Step 5 Preview measured |
| LMArena WebDev | Not measured | 1567 | Only Step 5 Preview measured |
| AA Coding Index | 22.1 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 31.8% | Only Step 5 Preview measured |
| Vibe Code Bench (Vals AI) | Not measured | 70.4% | Only Step 5 Preview measured |
| Code migration (Vals AI) | Not measured | 39.0% | Only Step 5 Preview measured |
| IOI (Vals AI) | Not measured | 38.1% | Only Step 5 Preview measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 40.8% | Only Step 5 Preview measured |
| SciCode | Not measured | 58.9% | Only Step 5 Preview measured |
| WeirdML | 41.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: coding | 1424 | 1485 | Step 5 Preview |
| LMArena Text: software and IT | 1431 | 1473 | Step 5 Preview |
| LMArena WebDev: React | Not measured | 1583 | Only Step 5 Preview measured |
| LMArena WebDev: HTML | Not measured | 1556 | Only Step 5 Preview measured |
| LMArena WebDev: from an image | Not measured | 1550 | Only Step 5 Preview measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 43.7 | Step 5 Preview |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 1.3 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LiveBench research | Not measured | 72.8% | Only Step 5 Preview measured |
| LiveBench browser | Not measured | 24.0% | Only Step 5 Preview measured |
| LiveBench long agentic | Not measured | 27.5% | Only Step 5 Preview measured |
| SREBench (Vals AI) | Not measured | 0.4% | Only Step 5 Preview measured |
| Finance Agent (Vals AI) | Not measured | 50.7% | Only Step 5 Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 27.3% | Only Step 5 Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 40.4% | Only Step 5 Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.1% | Only Step 5 Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 67.4% | Only Step 5 Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Step 5 Preview measured |
| Vals Science Index | Not measured | 29.6% | Only Step 5 Preview measured |
| Vending-Bench 2 | -$11 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 83.8% | Only Step 5 Preview measured |
| MysteryMechanism (Vals AI) | Not measured | 18.5% | Only Step 5 Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 46.5% | Only Step 5 Preview measured |
| GPQA Diamond (Epoch AI run) | 80.1% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Mystery game puzzles | 9.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: hard prompts | 1416 | 1461 | Step 5 Preview |
| LMArena Text: expert | 1463 | 1485 | Step 5 Preview |
| LMArena Text: hard prompts in English | 1432 | 1454 | Step 5 Preview |
| LMArena Vision: diagrams | Not measured | 1308 | Only Step 5 Preview measured |
| LMArena Vision: homework | Not measured | 1265 | Only Step 5 Preview measured |
| Neither model has a result on the other 12 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 86.7% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| ProofBench | Not measured | 42.0% | Only Step 5 Preview measured |
| LMArena Text: math | 1412 | 1458 | Step 5 Preview |
| LMArena Text: mathematical work | 1435 | 1460 | Step 5 Preview |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| SimpleQA Verified | 40.4% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: science | 1433 | 1454 | Step 5 Preview |
| LMArena Text: medicine and healthcare | 1456 | 1439 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: legal and government | 1415 | 1437 | Step 5 Preview |
| LMArena Text: business and finance | 1413 | 1435 | Step 5 Preview |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1052 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: UI components | 942 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: game dev | 956 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: data viz | 950 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: 3D | 997 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Design Arena: all code categories | 1032 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LiveBench design | Not measured | 76.9% | Only Step 5 Preview measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index112
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 63.5% | Only Step 5 Preview measured |
| Public Benefits Bench (Vals AI) | Not measured | 58.1% | Only Step 5 Preview measured |
| Long context reasoning (AA-LCR) | Not measured | 88.3% | Only Step 5 Preview measured |
| DTBench | 80.3% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMCA | 29.3% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Fiction.LiveBench | 75.0% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| Creative writing (Lech Mazur) | 82.4% | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text | 1415 | 1440 | Step 5 Preview |
| LMArena Text: instruction following | 1386 | 1438 | Step 5 Preview |
| LMArena Text: creative writing | 1384 | 1409 | Step 5 Preview |
| LMArena Vision | Not measured | 1265 | Only Step 5 Preview measured |
| LMArena Text: English | 1429 | 1447 | Step 5 Preview |
| LMArena Text: non-English | 1397 | 1428 | Step 5 Preview |
| LMArena Text: Chinese | 1481 | 1500 | Step 5 Preview |
| LMArena Text: German | 1408 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Japanese | 1386 | 1383 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Korean | 1375 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: French | Not measured | 1438 | Only Step 5 Preview measured |
| LMArena Text: Spanish | 1389 | 1441 | Step 5 Preview |
| LMArena Text: Russian | 1401 | 1433 | Step 5 Preview |
| LMArena Text: Polish | 1390 | Not measured | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: multi-turn | 1406 | 1437 | Step 5 Preview |
| LMArena Text: longer queries | 1400 | 1449 | Step 5 Preview |
| LMArena Text: writing and language | 1388 | 1425 | Step 5 Preview |
| LMArena Text: entertainment and media | 1370 | 1412 | Step 5 Preview |
| LMArena Vision: English | Not measured | 1290 | Only Step 5 Preview measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Step 5 Preview measured |
| Neither model has a result on the other 19 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3 235B A22B Thinking 2507 | Step 5 Preview | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Qwen3 235B A22B Thinking 2507 costs less
Repository review
50K input + 3K output tokens
Qwen3 235B A22B Thinking 2507 costs less
Agent loop
200K input + 10K output tokens
Qwen3 235B A22B Thinking 2507 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Qwen3 235B A22B Thinking 2507 | StepFun Step 5 Preview |
|---|---|---|
| Maker | Qwen | StepFun |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | October 8, 2026 |
| Context window | 128K | 1.05M |
| Input $/Mtok | $0.45 | $1.00 |
| Output $/Mtok | $3.50 | $2.70 |
| Coding index | Not benchmarked | 61.1 |
| Independent measurements behind it | 0 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3 235B A22B Thinking 2507 better than Step 5 Preview for coding?
Only Step 5 Preview has a coding score, 61.1 on the Vibe Coding Index; Qwen3 235B A22B Thinking 2507 has none, so the two cannot be ranked on coding. Pick Qwen3 235B A22B Thinking 2507 for work measured by LMArena Text: medicine and healthcare or LMArena Text: Japanese, where it leads.
Which is cheaper, Qwen3 235B A22B Thinking 2507 or Step 5 Preview?
Qwen3 235B A22B Thinking 2507 costs $0.45 per million input tokens and $3.50 per million output tokens; Step 5 Preview costs $1.00 and $2.70. Cost per solved task is known for neither of them.
Which has the bigger context window, Qwen3 235B A22B Thinking 2507 or Step 5 Preview?
Step 5 Preview, with 1.05M tokens against 128K.
How many benchmarks is the Qwen3 235B A22B Thinking 2507 vs Step 5 Preview comparison based on?
25 benchmarks have a result for both models as of October 22, 2026. Qwen3 235B A22B Thinking 2507's coding index rests on 0 independent benchmarks and Step 5 Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.