Qwen3.8 27B vs Qwen3.8 Max (0902)
Updated October 21, 2026. 82 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Qwen3.8 27B for coding: it scores 73.6 on the Vibe Coding Index against 63.5 for Qwen3.8 Max (0902).
Pick Qwen3.8 Max (0902) when what matters is LMArena WebDev or AA Coding Index, where it leads.
- Shared results
- 82
- Qwen3.8 27B only
- 3
- Qwen3.8 Max (0902) only
- 31
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Qwen3.8 27B
Qwen3.8 27B scores 73.6 against 63.5.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 45.4 against 33.7.
Same board, both measured
Agentic work
AA Agentic Index
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 56.0 against 45.8.
Same board, both measured
Reasoning
GPQA Diamond
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 93.7% against 88.9%.
Same board, both measured
Knowledge
MMLU Pro
Qwen3.8 Max (0902)
Qwen3.8 Max (0902) leads, 88.6% against 84.3%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Qwen3.8 Max (0902) has a Design Arena: websites result, 1275.
Directional only
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.8 27B
Qwen3.8 27B $0.0007, Qwen3.8 Max (0902) $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Qwen3.8 27B
Qwen3.8 27B $1.26, Qwen3.8 Max (0902) $1.32.
Published attempt cost and pass rate
At a glance
- Coding index
- Qwen3.8 27B 73.6 from 2 benchmarks, Qwen3.8 Max (0902) 63.5 from 2 benchmarks.
- Widest category
- Math, 18.5 points apart on average over 3 shared benchmarks.
- Widest single gap
- ProofBench: Qwen3.8 27B 16.0% against Qwen3.8 Max (0902) 58.0%, 42.0 points apart on a 0 to 100 scale.
- Output price
- Qwen3.8 27B $1.35 against Qwen3.8 Max (0902) $6.00 per million output tokens, 4.4x apart.
- Context window
- Both take 1M tokens.
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 | Qwen3.8 27B | Bars | Qwen3.8 Max (0902) | Ties |
|---|---|---|---|---|
| Coding | 4 | 13 | 1 tie | |
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 9 | 1 tie | |
| Reasoning | 0 | 10 | ||
| Math | 0 | 3 | ||
| Knowledge | 1 | 8 | ||
| Web design | 0 | 1 | ||
| General | 2 | 27 | ||
| All shared boards | 7 | 73 | 2 ties |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index413
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| LiveBench coding | 86.8% | 60.3% | Qwen3.8 27B |
| LMArena WebDev | 1593 | 1674 | Qwen3.8 Max (0902) |
| AA Coding Index | 68.1 | 76.2 | Qwen3.8 Max (0902) |
| LiveCodeBench (Vals AI) | 84.0% | 87.8% | Qwen3.8 Max (0902) |
| SWE-bench Verified (Vals AI) | 86.0% | 85.6% | Qwen3.8 27B |
| Terminal-Bench 4 (Vals AI) | Not measured | 34.3% | Only Qwen3.8 Max (0902) measured |
| Vibe Code Bench (Vals AI) | 64.8% | 64.7% | Qwen3.8 27B |
| Code migration (Vals AI) | 14.2% | 24.0% | Qwen3.8 Max (0902) |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | 39.1% | 68.9% | Qwen3.8 Max (0902) |
| Terminal-Bench 2.1 (Vals AI) | 58.4% | 67.4% | Qwen3.8 Max (0902) |
| SWE-bench Multimodal (Vals AI) | Not measured | 42.5% | Only Qwen3.8 Max (0902) measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 12.8% | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | 38.1% | 42.0% | Qwen3.8 Max (0902) |
| CyberBench (Vals AI) | 67.8% | 28.6% | Qwen3.8 27B |
| SciCode | 46.6% | 53.2% | Qwen3.8 Max (0902) |
| FrontierSWE | Not measured | 17.8% | Only Qwen3.8 Max (0902) measured |
| LMArena Text: coding | 1483 | 1502 | Qwen3.8 Max (0902) |
| LMArena Text: software and IT | 1478 | 1498 | Qwen3.8 Max (0902) |
| LMArena WebDev: React | 1602 | 1692 | Qwen3.8 Max (0902) |
| LMArena WebDev: HTML | 1570 | 1649 | Qwen3.8 Max (0902) |
| LMArena WebDev: from an image | 1577 | 1637 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | 45.4 | Qwen3.8 Max (0902) |
| Epoch Capabilities Index | 151.7 | 157.4 | Qwen3.8 Max (0902) |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| AA Agentic Index | 45.8 | 56.0 | Qwen3.8 Max (0902) |
| Design Arena: agents building web apps | Not measured | 1301 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building full-stack apps | Not measured | 1305 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building mobile apps | Not measured | 1223 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Android apps | Not measured | 1207 | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | Not measured | 1234 | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | Not measured | 1257 | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | Not measured | 868 | Only Qwen3.8 Max (0902) measured |
| LiveBench research | 59.4% | 69.9% | Qwen3.8 Max (0902) |
| LiveBench browser | 32.0% | 32.0% | Tie |
| LiveBench long agentic | 27.9% | 42.3% | Qwen3.8 Max (0902) |
| Finance Agent (Vals AI) | 48.5% | 50.6% | Qwen3.8 Max (0902) |
| Tax Agent Bench (Vals AI) | 30.9% | 32.1% | Qwen3.8 Max (0902) |
| Legal Research Bench (Vals AI) | 36.1% | 47.6% | Qwen3.8 Max (0902) |
| Excel Modeling Benchmark (Vals AI) | 59.7% | 60.1% | Qwen3.8 Max (0902) |
| Terminal-Bench-Science (Vals AI) | 0.0% | 12.9% | Qwen3.8 Max (0902) |
| APEX-Agents | 47.5% | 63.3% | Qwen3.8 Max (0902) |
| LMArena Search | Not measured | 1261 | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| GPQA Diamond | 88.9% | 93.7% | Qwen3.8 Max (0902) |
| LiveBench reasoning | 80.0% | 88.2% | Qwen3.8 Max (0902) |
| MysteryMechanism (Vals AI) | Not measured | 23.9% | Only Qwen3.8 Max (0902) measured |
| MMMU Pro (Vals AI) | 83.9% | 88.0% | Qwen3.8 Max (0902) |
| GPQA Diamond (Artificial Analysis run) | 90.5% | 92.8% | Qwen3.8 Max (0902) |
| Humanity's Last Exam (Artificial Analysis run) | 33.9% | 43.1% | Qwen3.8 Max (0902) |
| GPQA Diamond (Epoch AI run) | Not measured | 92.7% | Only Qwen3.8 Max (0902) measured |
| ARC-AGI | 87.5% | Not measured | Only Qwen3.8 27B measured |
| ARC-AGI-2 | 42.4% | Not measured | Only Qwen3.8 27B measured |
| Chess puzzles | Not measured | 46.0% | Only Qwen3.8 Max (0902) measured |
| Mystery game puzzles | Not measured | 38.0% | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts | 1459 | 1496 | Qwen3.8 Max (0902) |
| LMArena Text: expert | 1479 | 1507 | Qwen3.8 Max (0902) |
| LMArena Text: hard prompts in English | 1461 | 1503 | Qwen3.8 Max (0902) |
| LMArena Vision: diagrams | 1285 | 1323 | Qwen3.8 Max (0902) |
| LMArena Vision: homework | 1295 | 1336 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 100.0% | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tiers 1 to 3 | Not measured | 74.7% | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tier 4 | Not measured | 46.3% | Only Qwen3.8 Max (0902) measured |
| ProofBench | 16.0% | 58.0% | Qwen3.8 Max (0902) |
| LMArena Text: math | 1455 | 1501 | Qwen3.8 Max (0902) |
| LMArena Text: mathematical work | 1458 | 1491 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| MMLU Pro | 84.3% | 88.6% | Qwen3.8 Max (0902) |
| LegalBench (Vals AI) | 82.4% | 83.6% | Qwen3.8 Max (0902) |
| CorpFin (Vals AI) | Not measured | 65.8% | Only Qwen3.8 Max (0902) measured |
| TaxEval (Vals AI) | 70.8% | 75.5% | Qwen3.8 Max (0902) |
| MortgageTax (Vals AI) | 64.9% | 64.0% | Qwen3.8 27B |
| MedCode (Vals AI) | 28.7% | 40.7% | Qwen3.8 Max (0902) |
| SimpleQA Verified | Not measured | 47.3% | Only Qwen3.8 Max (0902) measured |
| LMArena Text: science | 1467 | 1512 | Qwen3.8 Max (0902) |
| LMArena Text: medicine and healthcare | 1437 | 1503 | Qwen3.8 Max (0902) |
| LMArena Text: legal and government | 1447 | 1492 | Qwen3.8 Max (0902) |
| LMArena Text: business and finance | 1438 | 1480 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1275 | Only Qwen3.8 Max (0902) measured |
| Design Arena: UI components | Not measured | 1340 | Only Qwen3.8 Max (0902) measured |
| Design Arena: game dev | Not measured | 1313 | Only Qwen3.8 Max (0902) measured |
| Design Arena: data viz | Not measured | 1281 | Only Qwen3.8 Max (0902) measured |
| Design Arena: 3D | Not measured | 1337 | Only Qwen3.8 Max (0902) measured |
| Design Arena: all code categories | Not measured | 1293 | Only Qwen3.8 Max (0902) measured |
| Design Arena: ASCII art | Not measured | 1201 | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 75.9% | 78.6% | Qwen3.8 Max (0902) |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index227
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| LiveBench data analysis | 76.6% | 78.4% | Qwen3.8 Max (0902) |
| Public Benefits Bench (Vals AI) | Not measured | 67.1% | Only Qwen3.8 Max (0902) measured |
| SAGE (Vals AI) | 52.4% | 51.2% | Qwen3.8 27B |
| MedScribe (Vals AI) | 83.8% | 85.0% | Qwen3.8 Max (0902) |
| Vals Multimodal Index | Not measured | 65.4% | Only Qwen3.8 Max (0902) measured |
| Long context reasoning (AA-LCR) | 82.0% | 80.3% | Qwen3.8 27B |
| DTBench | 88.0% | 92.0% | Qwen3.8 Max (0902) |
| LMCA | 41.4% | 46.2% | Qwen3.8 Max (0902) |
| Surface Evolver Bench | 45.0% | Not measured | Only Qwen3.8 27B measured |
| Furniture assembly | Not measured | 20.0% | Only Qwen3.8 Max (0902) measured |
| LMArena Text | 1440 | 1483 | Qwen3.8 Max (0902) |
| LMArena Text: instruction following | 1436 | 1481 | Qwen3.8 Max (0902) |
| LMArena Text: creative writing | 1383 | 1477 | Qwen3.8 Max (0902) |
| LMArena Vision | 1269 | 1313 | Qwen3.8 Max (0902) |
| LMArena Text: English | 1448 | 1491 | Qwen3.8 Max (0902) |
| LMArena Text: non-English | 1428 | 1473 | Qwen3.8 Max (0902) |
| LMArena Text: Chinese | 1501 | 1539 | Qwen3.8 Max (0902) |
| LMArena Text: German | 1443 | 1478 | Qwen3.8 Max (0902) |
| LMArena Text: Japanese | 1387 | 1473 | Qwen3.8 Max (0902) |
| LMArena Text: Korean | 1384 | 1460 | Qwen3.8 Max (0902) |
| LMArena Text: French | 1465 | 1498 | Qwen3.8 Max (0902) |
| LMArena Text: Spanish | 1449 | 1489 | Qwen3.8 Max (0902) |
| LMArena Text: Russian | 1415 | 1482 | Qwen3.8 Max (0902) |
| LMArena Text: Polish | 1439 | 1471 | Qwen3.8 Max (0902) |
| LMArena Text: multi-turn | 1440 | 1489 | Qwen3.8 Max (0902) |
| LMArena Text: longer queries | 1448 | 1488 | Qwen3.8 Max (0902) |
| LMArena Text: writing and language | 1405 | 1477 | Qwen3.8 Max (0902) |
| LMArena Text: entertainment and media | 1393 | 1464 | Qwen3.8 Max (0902) |
| LMArena Vision: English | 1267 | 1311 | Qwen3.8 Max (0902) |
| LMArena Vision: Chinese | 1326 | 1358 | Qwen3.8 Max (0902) |
| LMArena Vision: reading text | 1281 | 1322 | Qwen3.8 Max (0902) |
| LMArena Vision: humor | 1235 | 1304 | Qwen3.8 Max (0902) |
| LMArena Vision: creative writing | 1237 | 1312 | Qwen3.8 Max (0902) |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.8 27B | Qwen3.8 Max (0902) | 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
Qwen3.8 27B costs less
Repository review
50K input + 3K output tokens
Qwen3.8 27B costs less
Agent loop
200K input + 10K output tokens
Qwen3.8 27B 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 | Qwen3.8 27B | Qwen3.8 Max (0902) |
|---|---|---|
| Maker | Qwen | Qwen |
| Weights | Open weights | No public weights listed |
| Released | August 14, 2026 | September 3, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $0.04 | $2.00 |
| Output $/Mtok | $1.35 | $6.00 |
| Coding index | 73.6 | 63.5 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.26 | $1.32 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.8 27B better than Qwen3.8 Max (0902) for coding?
Pick Qwen3.8 27B for coding: it scores 73.6 on the Vibe Coding Index against 63.5 for Qwen3.8 Max (0902). Pick Qwen3.8 Max (0902) when what matters is LMArena WebDev or AA Coding Index, where it leads.
Which is cheaper, Qwen3.8 27B or Qwen3.8 Max (0902)?
Qwen3.8 27B costs $0.04 per million input tokens and $1.35 per million output tokens; Qwen3.8 Max (0902) costs $2.00 and $6.00. Per solved SWE-bench Verified task, Qwen3.8 27B costs $1.26 and Qwen3.8 Max (0902) $1.32.
Which has the bigger context window, Qwen3.8 27B or Qwen3.8 Max (0902)?
Neither: both take 1M tokens.
How many benchmarks is the Qwen3.8 27B vs Qwen3.8 Max (0902) comparison based on?
82 benchmarks have a result for both models as of October 21, 2026. Qwen3.8 27B's coding index rests on 2 independent benchmarks and Qwen3.8 Max (0902)'s on 2. Where only one model has a result, the page says so instead of naming a winner.