Claude Haiku 5.5 vs Qwen4 Max
Qwen4 Max leads Claude Haiku 5.5 on coding, 74.0 to 68.5 on the Vibe Coding Index, and Claude Haiku 5.5 costs 8.6x less per output token ($0.50 vs $4.275 per million). Updated November 22, 2026; 25 benchmarks have a result for both.
Claude Haiku 5.5 or Qwen4 Max: which to pick
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 68.5 for Claude Haiku 5.5, though on 4 benchmarks against 5.
Pick Claude Haiku 5.5 for output tokens 8.6x cheaper ($0.50 vs $4.275 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 25
- Claude Haiku 5.5 only
- 84
- Qwen4 Max only
- 1
- Like-for-like categories
- 7 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
Qwen4 Max
Qwen4 Max scores 74.0 against 68.5.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen4 Max
Qwen4 Max leads, 42.9 against 36.5.
Same board, both measured
Web design
Design Arena: websites
No call
Only Claude Haiku 5.5 has a Design Arena: websites result, 1248.
Directional only
General
Vals Index
Qwen4 Max
Qwen4 Max leads, 63.2% against 58.7%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 $0.0003, Qwen4 Max $0.0036 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 68.5 from 5 benchmarks, Qwen4 Max 74.0 from 4 benchmarks.
- Widest category
- General, 16.6 points apart on average over 3 shared benchmarks.
- Widest single gap
- LiveBench data analysis: Claude Haiku 5.5 53.1% against Qwen4 Max 83.4%, 30.3 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against Qwen4 Max $4.275 per million output tokens, 8.6x 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 | Claude Haiku 5.5 | Bars | Qwen4 Max | Ties |
|---|---|---|---|---|
| Coding | 3 | 7 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 2 | 4 | ||
| Reasoning | 1 | 2 | ||
| Knowledge | 0 | 1 | ||
| Web design | 1 | 0 | ||
| General | 0 | 3 | ||
| All shared boards | 7 | 18 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index37
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench coding | 77.6% | 69.8% | Claude Haiku 5.5 |
| LMArena WebDev | 1595 | 1751 | Qwen4 Max |
| Terminal-Bench 4 (Vals AI) | 36.4% | 48.5% | Qwen4 Max |
| Vibe Code Bench (Vals AI) | 90.4% | 86.7% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | Not measured | Only Claude Haiku 5.5 measured |
| ProgramBench (Vals AI) | 2.5% | Not measured | Only Claude Haiku 5.5 measured |
| IOI (Vals AI) | 47.3% | Not measured | Only Claude Haiku 5.5 measured |
| SWE-bench Multimodal (Vals AI) | 44.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench 1-100 (Vals AI) | 20.4% | Not measured | Only Claude Haiku 5.5 measured |
| CyberBench (Vals AI) | 75.5% | Not measured | Only Claude Haiku 5.5 measured |
| SciCode | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 32.8% | 48.5% | Qwen4 Max |
| FrontierCode 2.0 | 34.9% | 26.5% | Claude Haiku 5.5 |
| FrontierCode | 46.4% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| MirrorCode | 78.9% | Not measured | Only Claude Haiku 5.5 measured |
| ALE-Bench | 1587.0 | 1831.0 | Qwen4 Max |
| LMArena Text: coding | 1452 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: software and IT | 1441 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev: React | 1618 | 1785 | Qwen4 Max |
| LMArena WebDev: HTML | 1569 | 1752 | Qwen4 Max |
| LMArena WebDev: from an image | Not measured | 1675 | Only Qwen4 Max measured |
| SciCode | 9.2% | Not measured | Only Claude Haiku 5.5 measured |
| SWE-Bench Pro V2 | 87.2% | Not measured | Only Claude Haiku 5.5 measured |
| GameBench 2 | 74.9 | 82.4 | Qwen4 Max |
| Terminal-Bench 4.0 | 40.0% | Not measured | Only Claude Haiku 5.5 measured |
| CursorBench 4.0 | 48.4% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| AA Intelligence Index | 36.5 | 42.9 | Qwen4 Max |
| Epoch Capabilities Index | 160.3 | Not measured | Only Claude Haiku 5.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench research | 84.3% | 84.7% | Qwen4 Max |
| LiveBench browser | 69.5% | 80.7% | Qwen4 Max |
| LiveBench long agentic | 47.9% | 46.6% | Claude Haiku 5.5 |
| SREBench (Vals AI) | 5.7% | Not measured | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | 54.1% | Not measured | Only Claude Haiku 5.5 measured |
| Tax Agent Bench (Vals AI) | 31.9% | 40.4% | Qwen4 Max |
| Legal Research Bench (Vals AI) | 43.8% | 41.4% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | 21.3% | Qwen4 Max |
| Excel Modeling Benchmark (Vals AI) | 59.0% | Not measured | Only Claude Haiku 5.5 measured |
| BioMysteryBench (Vals AI) | 70.4% | Not measured | Only Claude Haiku 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 10.0% | Not measured | Only Claude Haiku 5.5 measured |
| Vals Science Index | 38.5% | Not measured | Only Claude Haiku 5.5 measured |
| APEX-Agents | 56.1% | Not measured | Only Claude Haiku 5.5 measured |
| Vending-Bench 2 | $3,602 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | 92.2% | Qwen4 Max |
| MysteryMechanism (Vals AI) | 35.1% | Not measured | Only Claude Haiku 5.5 measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | Not measured | Only Claude Haiku 5.5 measured |
| HLE-Diamond (Artificial Analysis run) | 29.6% | 44.9% | Qwen4 Max |
| CritPt v2, hard subset (Artificial Analysis run) | 47.5% | 43.0% | Claude Haiku 5.5 |
| GPQA Diamond (Epoch AI run) | 89.6% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI | 89.0% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI-2 | 61.3% | Not measured | Only Claude Haiku 5.5 measured |
| SimpleBench | 59.2% | Not measured | Only Claude Haiku 5.5 measured |
| Chess puzzles | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Mystery game puzzles | 30.0% | Not measured | Only Claude Haiku 5.5 measured |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | 1416 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: expert | 1438 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts in English | 1420 | Not measured | Only Claude Haiku 5.5 measured |
| Humanity's Last Exam (Scale run) | 21.1% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 10 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierMath, tiers 1 to 3 | 75.1% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierMath, tier 4 | 46.3% | Not measured | Only Claude Haiku 5.5 measured |
| ProofBench | 89.0% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: math | 1433 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: mathematical work | 1432 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | Not measured | Only Claude Haiku 5.5 measured |
| AA-Omniscience | 12.3 | 27.7 | Qwen4 Max |
| SimpleQA Verified | 23.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: science | 1415 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: medicine and healthcare | 1377 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: legal and government | 1390 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: business and finance | 1392 | Not measured | Only Claude Haiku 5.5 measured |
| FACTS Benchmark Suite | 47.3% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 13 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| Design Arena: websites | 1248 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: UI components | 1259 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: game dev | 1313 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: data viz | 1276 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: 3D | 1307 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: all code categories | 1273 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: SVG | 1201 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: ASCII art | 1213 | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench design | 79.3% | 79.1% | Claude Haiku 5.5 |
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | Leader |
|---|---|---|---|
| Vals Index | 58.7% | 63.2% | Qwen4 Max |
| LiveBench data analysis | 53.1% | 83.4% | Qwen4 Max |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 89.8% | Not measured | Only Claude Haiku 5.5 measured |
| MedScribe (Vals AI) | 89.5% | Not measured | Only Claude Haiku 5.5 measured |
| Long context reasoning (AA-LCR) | 82.7% | Not measured | Only Claude Haiku 5.5 measured |
| GDPval-AA | 1629 | 1809 | Qwen4 Max |
| DTBench | 95.0% | Not measured | Only Claude Haiku 5.5 measured |
| LMCA | 51.1% | Not measured | Only Claude Haiku 5.5 measured |
| Furniture assembly | 47.5% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text | 1398 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: instruction following | 1407 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: creative writing | 1334 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: English | 1405 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: non-English | 1385 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Chinese | 1435 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: German | 1427 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Japanese | 1378 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Korean | 1375 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: French | 1425 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Spanish | 1396 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Russian | 1379 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Polish | 1385 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: multi-turn | 1387 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: longer queries | 1392 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: writing and language | 1366 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: entertainment and media | 1350 | Not measured | Only Claude Haiku 5.5 measured |
| MultiChallenge | 67.7% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | Qwen4 Max | 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
Claude Haiku 5.5 costs less
Repository review
50K input + 3K output tokens
Claude Haiku 5.5 costs less
Agent loop
200K input + 10K output tokens
Claude Haiku 5.5 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 | Anthropic Claude Haiku 5.5 | Qwen4 Max |
|---|---|---|
| Maker | Anthropic | Qwen |
| Weights | No public weights listed | No public weights listed |
| Released | October 7, 2026 | November 16, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $0.10 | $1.425 |
| Output $/Mtok | $0.50 | $4.275 |
| Coding index | 68.5 | 74.0 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than Qwen4 Max for coding?
Pick Qwen4 Max for coding: it scores 74.0 on the Vibe Coding Index against 68.5 for Claude Haiku 5.5, though on 4 benchmarks against 5. Pick Claude Haiku 5.5 for output tokens 8.6x cheaper ($0.50 vs $4.275 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.
Which is cheaper, Claude Haiku 5.5 or Qwen4 Max?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen4 Max costs $1.425 and $4.275. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or Qwen4 Max?
Neither: both take 1M tokens.
How many benchmarks is the Claude Haiku 5.5 vs Qwen4 Max comparison based on?
25 benchmarks have a result for both models as of November 22, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Qwen4 Max's on 4. Where only one model has a result, the page says so instead of naming a winner.