Qwen3.8 Max (0902) vs Hy4
Qwen3.8 Max (0902) leads Hy4 on coding, 67.1 to 65.2 on the Vibe Coding Index, and Hy4 costs 4.8x less per output token ($1.2505 vs $6.00 per million). Updated November 5, 2026; 6 benchmarks have a result for both.
Qwen3.8 Max (0902) or Hy4: which to pick
Qwen3.8 Max (0902) and Hy4 are level for coding, 67.1 against 65.2 on the Vibe Coding Index, so price and context decide.
Pick Hy4 for output tokens 4.8x cheaper ($1.2505 vs $6.00 per million) and a larger context window (1.05M against 1M tokens). Pick Qwen3.8 Max (0902) for work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
- Shared results
- 6
- Qwen3.8 Max (0902) only
- 114
- Hy4 only
- 0
- Like-for-like categories
- 3 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
Level: 67.1 against 65.2, inside 2 points.
5 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Qwen3.8 Max (0902) has a AA Intelligence Index result, 33.7.
Directional only
Agentic work
AA Agentic Index
No call
Only Qwen3.8 Max (0902) has a AA Agentic Index result, 56.0.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 Max (0902) has a GPQA Diamond result, 93.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 Max (0902) has a MMLU Pro result, 88.6%.
Directional only
Web design
Design Arena: websites
No call
Only Qwen3.8 Max (0902) has a Design Arena: websites result, 1274.
Directional only
General
Vals Index
Hy4
Hy4 leads, 59.4% against 59.1%.
Same board, both measured
Long documents
Listed context window
Hy4
Hy4 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4
Qwen3.8 Max (0902) $0.0050, Hy4 $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 Max (0902) has the number, $1.32.
Directional only
At a glance
- Coding index
- Qwen3.8 Max (0902) 67.1 from 5 benchmarks, Hy4 65.2 from 2 benchmarks.
- Widest category
- Agentic work, 8.1 points apart on average over 3 shared benchmarks.
- Widest single gap
- Tax Agent Bench (Vals AI): Qwen3.8 Max (0902) 49.7% against Hy4 34.4%, 15.3 points apart on a 0 to 100 scale.
- Output price
- Qwen3.8 Max (0902) $6.00 against Hy4 $1.2505 per million output tokens, 4.8x apart.
- Context window
- Qwen3.8 Max (0902) takes 1M tokens, Hy4 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 | Qwen3.8 Max (0902) | Bars | Hy4 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Agentic work | 3 | 0 | ||
| General | 0 | 1 | ||
| All shared boards | 3 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| LiveBench coding | 60.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev | 1676 | Not measured | Only Qwen3.8 Max (0902) measured |
| AA Coding Index | 76.2 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveCodeBench (Vals AI) | 87.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-bench Verified (Vals AI) | 85.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4 (Vals AI) | 38.9% | 39.4% | Hy4 |
| Vibe Code Bench (Vals AI) | 77.1% | 81.0% | Hy4 |
| Code migration (Vals AI) | 24.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| IOI (Vals AI) | 68.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 2.1 (Vals AI) | 67.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| SWE-bench Multimodal (Vals AI) | 42.5% | Not measured | Only Qwen3.8 Max (0902) measured |
| Vibe Code Bench 1-100 (Vals AI) | 24.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| SkillsBench (Vals AI) | 42.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| CyberBench (Vals AI) | 28.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| SciCode | 53.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierSWE | 17.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| ALE-Bench | 1679.1 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: coding | 1504 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: software and IT | 1499 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev: React | 1692 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev: HTML | 1657 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena WebDev: from an image | 1637 | Not measured | Only Qwen3.8 Max (0902) measured |
| GameBench 2 | 68.1 | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench 4.0 | 27.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 33.7 | Not measured | Only Qwen3.8 Max (0902) measured |
| Epoch Capabilities Index | 157.4 | Not measured | Only Qwen3.8 Max (0902) measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| AA Agentic Index | 56.0 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building web apps | 1288 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building full-stack apps | 1301 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building mobile apps | 1224 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Android apps | 1205 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: agents building Godot games | 1235 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: PowerPoint slides | 1217 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: spreadsheets | 1056 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench research | 69.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench browser | 49.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench long agentic | 29.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| Finance Agent (Vals AI) | 57.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| Tax Agent Bench (Vals AI) | 49.7% | 34.4% | Qwen3.8 Max (0902) |
| Legal Research Bench (Vals AI) | 47.6% | 41.4% | Qwen3.8 Max (0902) |
| Harvey's Legal Agent Benchmark (Vals AI) | 15.4% | 12.5% | Qwen3.8 Max (0902) |
| Excel Modeling Benchmark (Vals AI) | 72.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Terminal-Bench-Science (Vals AI) | 12.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| APEX-Agents | 63.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Search | 1261 | Not measured | Only Qwen3.8 Max (0902) measured |
| τ³-Banking | 55.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index14 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| GPQA Diamond | 93.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench reasoning | 88.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| MysteryMechanism (Vals AI) | 23.9% | Not measured | Only Qwen3.8 Max (0902) measured |
| MMMU Pro (Vals AI) | 88.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Artificial Analysis run) | 92.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.1% | Not measured | Only Qwen3.8 Max (0902) measured |
| GPQA Diamond (Epoch AI run) | 92.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| Chess puzzles | 46.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Mystery game puzzles | 38.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts | 1496 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: expert | 1508 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: hard prompts in English | 1505 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: diagrams | 1323 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: homework | 1336 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tiers 1 to 3 | 74.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| ProofBench | 58.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: math | 1506 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: mathematical work | 1496 | Not measured | Only Qwen3.8 Max (0902) measured |
| MathArena | 51.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| MMLU Pro | 88.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| LegalBench (Vals AI) | 83.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| CorpFin (Vals AI) | 65.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| TaxEval (Vals AI) | 75.5% | Not measured | Only Qwen3.8 Max (0902) measured |
| MortgageTax (Vals AI) | 64.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| MedCode (Vals AI) | 40.7% | Not measured | Only Qwen3.8 Max (0902) measured |
| SimpleQA Verified | 47.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: science | 1514 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: medicine and healthcare | 1505 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: legal and government | 1494 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: business and finance | 1480 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1274 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: UI components | 1335 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: game dev | 1314 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: data viz | 1284 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: 3D | 1334 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: all code categories | 1292 | Not measured | Only Qwen3.8 Max (0902) measured |
| Design Arena: ASCII art | 1193 | Not measured | Only Qwen3.8 Max (0902) measured |
| LiveBench design | 78.6% | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Qwen3.8 Max (0902) | Hy4 | Leader |
|---|---|---|---|
| Vals Index | 59.1% | 59.4% | Hy4 |
| LiveBench data analysis | 78.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Public Benefits Bench (Vals AI) | 67.1% | Not measured | Only Qwen3.8 Max (0902) measured |
| SAGE (Vals AI) | 81.8% | Not measured | Only Qwen3.8 Max (0902) measured |
| MedScribe (Vals AI) | 85.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| Vals Multimodal Index | 65.4% | Not measured | Only Qwen3.8 Max (0902) measured |
| Long context reasoning (AA-LCR) | 80.3% | Not measured | Only Qwen3.8 Max (0902) measured |
| DTBench | 92.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMCA | 46.2% | Not measured | Only Qwen3.8 Max (0902) measured |
| Furniture assembly | 20.0% | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text | 1483 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: instruction following | 1480 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: creative writing | 1478 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision | 1313 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: English | 1493 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: non-English | 1472 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Chinese | 1540 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: German | 1475 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Japanese | 1471 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Korean | 1462 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: French | 1503 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Spanish | 1488 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Russian | 1484 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: Polish | 1475 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: multi-turn | 1491 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: longer queries | 1488 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: writing and language | 1478 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Text: entertainment and media | 1465 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: English | 1311 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: Chinese | 1358 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: reading text | 1322 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: humor | 1304 | Not measured | Only Qwen3.8 Max (0902) measured |
| LMArena Vision: creative writing | 1312 | Not measured | Only Qwen3.8 Max (0902) measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Qwen3.8 Max (0902) | Hy4 | 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
Hy4 costs less
Repository review
50K input + 3K output tokens
Hy4 costs less
Agent loop
200K input + 10K output tokens
Hy4 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 Max (0902) | Tencent Hy4 |
|---|---|---|
| Maker | Qwen | Tencent |
| Weights | No public weights listed | Open weights |
| Released | September 3, 2026 | November 4, 2026 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $2.00 | $0.417 |
| Output $/Mtok | $6.00 | $1.2505 |
| Coding index | 67.1 | 65.2 |
| Independent measurements behind it | 5 | 2 |
| Cost per solved task | $1.32 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Qwen3.8 Max (0902) better than Hy4 for coding?
Qwen3.8 Max (0902) and Hy4 are level for coding, 67.1 against 65.2 on the Vibe Coding Index, so price and context decide. Pick Hy4 for output tokens 4.8x cheaper ($1.2505 vs $6.00 per million) and a larger context window (1.05M against 1M tokens). Pick Qwen3.8 Max (0902) for work measured by Tax Agent Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
Which is cheaper, Qwen3.8 Max (0902) or Hy4?
Qwen3.8 Max (0902) costs $2.00 per million input tokens and $6.00 per million output tokens; Hy4 costs $0.417 and $1.2505. Cost per solved task is known for Qwen3.8 Max (0902) only.
Which has the bigger context window, Qwen3.8 Max (0902) or Hy4?
Hy4, with 1.05M tokens against 1M.
How many benchmarks is the Qwen3.8 Max (0902) vs Hy4 comparison based on?
6 benchmarks have a result for both models as of November 5, 2026. Qwen3.8 Max (0902)'s coding index rests on 5 independent benchmarks and Hy4's on 2. Where only one model has a result, the page says so instead of naming a winner.