Claude Haiku 5.5 vs Qwen3.8 27B
Qwen3.8 27B leads Claude Haiku 5.5 on coding, 74.2 to 70.7 on the Vibe Coding Index, and Claude Haiku 5.5 costs 5.1x less per output token ($0.50 vs $2.55 per million). Updated October 22, 2026; 34 benchmarks have a result for both.
Claude Haiku 5.5 or Qwen3.8 27B: which to pick
Pick Qwen3.8 27B for coding: it scores 74.2 on the Vibe Coding Index against 70.7 for Claude Haiku 5.5, though on 4 benchmarks against 5.
Pick Claude Haiku 5.5 for output tokens 5.1x cheaper ($0.50 vs $2.55 per million) and work measured by LiveBench coding or Vibe Code Bench (Vals AI), where it leads.
- Shared results
- 34
- Claude Haiku 5.5 only
- 31
- Qwen3.8 27B only
- 51
- Like-for-like categories
- 8 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
Qwen3.8 27B
Qwen3.8 27B scores 74.2 against 70.7.
5 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 against 33.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.8 27B has a AA Agentic Index result, 45.8.
Directional only
Reasoning
GPQA Diamond
No call
Only Qwen3.8 27B has a GPQA Diamond result, 88.9%.
Directional only
Knowledge
MMLU Pro
No call
Only Qwen3.8 27B has a MMLU Pro result, 84.3%.
Directional only
Web design
Design Arena: websites
No call
Only Claude Haiku 5.5 has a Design Arena: websites result, 1262.
Directional only
General
Vals Index
No call
Only Claude Haiku 5.5 has a Vals Index result, 58.7%.
Directional only
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, Qwen3.8 27B $0.0017 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Qwen3.8 27B has the number, $1.26.
Directional only
At a glance
- Coding index
- Claude Haiku 5.5 70.7 from 5 benchmarks, Qwen3.8 27B 74.2 from 4 benchmarks.
- Widest category
- Math, 73.0 points apart on average over 1 shared benchmark.
- Widest single gap
- ProofBench: Claude Haiku 5.5 89.0% against Qwen3.8 27B 16.0%, 73.0 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against Qwen3.8 27B $2.55 per million output tokens, 5.1x 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 | Qwen3.8 27B | Ties |
|---|---|---|---|---|
| Coding | 8 | 2 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 8 | 1 | ||
| Reasoning | 4 | 0 | ||
| Math | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 1 | 0 | ||
| General | 4 | 2 | ||
| All shared boards | 29 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index82
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | 86.8% | Claude Haiku 5.5 |
| LMArena WebDev | 1586 | 1593 | Qwen3.8 27B |
| AA Coding Index | Not measured | 68.1 | Only Qwen3.8 27B measured |
| LiveCodeBench (Vals AI) | Not measured | 84.0% | Only Qwen3.8 27B measured |
| SWE-bench Verified (Vals AI) | Not measured | 86.0% | Only Qwen3.8 27B measured |
| Terminal-Bench 4 (Vals AI) | 36.4% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench (Vals AI) | 90.4% | 64.8% | Claude Haiku 5.5 |
| Code migration (Vals AI) | 44.6% | 14.2% | Claude Haiku 5.5 |
| ProgramBench (Vals AI) | 2.5% | 0.0% | Claude Haiku 5.5 |
| IOI (Vals AI) | 47.3% | 39.1% | Claude Haiku 5.5 |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 58.4% | Only Qwen3.8 27B 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 |
| SkillsBench (Vals AI) | Not measured | 38.1% | Only Qwen3.8 27B measured |
| CyberBench (Vals AI) | 75.5% | 67.8% | Claude Haiku 5.5 |
| SciCode | 55.0% | 46.6% | 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 |
| LMArena Text: coding | Not measured | 1483 | Only Qwen3.8 27B measured |
| LMArena Text: software and IT | Not measured | 1478 | Only Qwen3.8 27B measured |
| LMArena WebDev: React | 1605 | 1602 | Claude Haiku 5.5 |
| LMArena WebDev: HTML | 1569 | 1570 | Qwen3.8 27B |
| LMArena WebDev: from an image | Not measured | 1577 | Only Qwen3.8 27B 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 |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 33.7 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 159.3 | 151.7 | Claude Haiku 5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index81
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 45.8 | Only Qwen3.8 27B measured |
| LiveBench research | 81.9% | 59.4% | Claude Haiku 5.5 |
| LiveBench browser | 80.0% | 32.0% | Claude Haiku 5.5 |
| LiveBench long agentic | 57.6% | 27.9% | Claude Haiku 5.5 |
| SREBench (Vals AI) | 5.7% | Not measured | Only Claude Haiku 5.5 measured |
| Finance Agent (Vals AI) | 54.1% | 48.5% | Claude Haiku 5.5 |
| Tax Agent Bench (Vals AI) | 31.9% | 30.9% | Claude Haiku 5.5 |
| Legal Research Bench (Vals AI) | 43.3% | 36.1% | Claude Haiku 5.5 |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | Not measured | Only Claude Haiku 5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 59.0% | 59.7% | Qwen3.8 27B |
| BioMysteryBench (Vals AI) | 70.4% | Not measured | Only Claude Haiku 5.5 measured |
| Terminal-Bench-Science (Vals AI) | 10.0% | 0.0% | Claude Haiku 5.5 |
| Vals Science Index | 38.5% | Not measured | Only Claude Haiku 5.5 measured |
| APEX-Agents | 56.1% | 47.5% | Claude Haiku 5.5 |
| Vending-Bench 2 | $3,602 | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 88.9% | Only Qwen3.8 27B measured |
| LiveBench reasoning | 82.4% | 80.0% | Claude Haiku 5.5 |
| MysteryMechanism (Vals AI) | 35.1% | Not measured | Only Claude Haiku 5.5 measured |
| MMMU Pro (Vals AI) | Not measured | 83.9% | Only Qwen3.8 27B measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 90.5% | Only Qwen3.8 27B measured |
| Humanity's Last Exam (Artificial Analysis run) | 44.4% | 33.9% | Claude Haiku 5.5 |
| GPQA Diamond (Epoch AI run) | 89.6% | Not measured | Only Claude Haiku 5.5 measured |
| ARC-AGI | 89.0% | 87.5% | Claude Haiku 5.5 |
| ARC-AGI-2 | 61.3% | 42.4% | Claude Haiku 5.5 |
| 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 | Not measured | 1459 | Only Qwen3.8 27B measured |
| LMArena Text: expert | Not measured | 1479 | Only Qwen3.8 27B measured |
| LMArena Text: hard prompts in English | Not measured | 1461 | Only Qwen3.8 27B measured |
| LMArena Vision: diagrams | Not measured | 1285 | Only Qwen3.8 27B measured |
| LMArena Vision: homework | Not measured | 1295 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | 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% | 16.0% | Claude Haiku 5.5 |
| LMArena Text: math | Not measured | 1455 | Only Qwen3.8 27B measured |
| LMArena Text: mathematical work | Not measured | 1458 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 84.3% | Only Qwen3.8 27B measured |
| LegalBench (Vals AI) | Not measured | 82.4% | Only Qwen3.8 27B measured |
| TaxEval (Vals AI) | Not measured | 70.8% | Only Qwen3.8 27B measured |
| MortgageTax (Vals AI) | Not measured | 64.9% | Only Qwen3.8 27B measured |
| MedCode (Vals AI) | 51.5% | 28.7% | Claude Haiku 5.5 |
| SimpleQA Verified | 23.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: science | Not measured | 1467 | Only Qwen3.8 27B measured |
| LMArena Text: medicine and healthcare | Not measured | 1437 | Only Qwen3.8 27B measured |
| LMArena Text: legal and government | Not measured | 1447 | Only Qwen3.8 27B measured |
| LMArena Text: business and finance | Not measured | 1438 | Only Qwen3.8 27B measured |
| Neither model has a result on the other 10 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: UI components | 1283 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: game dev | 1315 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: data viz | 1297 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: 3D | 1342 | Not measured | Only Claude Haiku 5.5 measured |
| Design Arena: all code categories | 1278 | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench design | 83.1% | 75.9% | Claude Haiku 5.5 |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | Leader |
|---|---|---|---|
| Vals Index | 58.7% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench data analysis | 53.1% | 76.6% | Qwen3.8 27B |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 45.8% | 52.4% | Qwen3.8 27B |
| MedScribe (Vals AI) | 89.5% | 83.8% | Claude Haiku 5.5 |
| Long context reasoning (AA-LCR) | 82.7% | 82.0% | Claude Haiku 5.5 |
| DTBench | 95.0% | 88.0% | Claude Haiku 5.5 |
| LMCA | 51.1% | 41.4% | Claude Haiku 5.5 |
| Surface Evolver Bench | Not measured | 45.0% | Only Qwen3.8 27B measured |
| Furniture assembly | 47.5% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text | Not measured | 1440 | Only Qwen3.8 27B measured |
| LMArena Text: instruction following | Not measured | 1436 | Only Qwen3.8 27B measured |
| LMArena Text: creative writing | Not measured | 1383 | Only Qwen3.8 27B measured |
| LMArena Vision | Not measured | 1269 | Only Qwen3.8 27B measured |
| LMArena Text: English | Not measured | 1448 | Only Qwen3.8 27B measured |
| LMArena Text: non-English | Not measured | 1428 | Only Qwen3.8 27B measured |
| LMArena Text: Chinese | Not measured | 1501 | Only Qwen3.8 27B measured |
| LMArena Text: German | Not measured | 1443 | Only Qwen3.8 27B measured |
| LMArena Text: Japanese | Not measured | 1387 | Only Qwen3.8 27B measured |
| LMArena Text: Korean | Not measured | 1384 | Only Qwen3.8 27B measured |
| LMArena Text: French | Not measured | 1465 | Only Qwen3.8 27B measured |
| LMArena Text: Spanish | Not measured | 1449 | Only Qwen3.8 27B measured |
| LMArena Text: Russian | Not measured | 1415 | Only Qwen3.8 27B measured |
| LMArena Text: Polish | Not measured | 1439 | Only Qwen3.8 27B measured |
| LMArena Text: multi-turn | Not measured | 1440 | Only Qwen3.8 27B measured |
| LMArena Text: longer queries | Not measured | 1448 | Only Qwen3.8 27B measured |
| LMArena Text: writing and language | Not measured | 1405 | Only Qwen3.8 27B measured |
| LMArena Text: entertainment and media | Not measured | 1393 | Only Qwen3.8 27B measured |
| LMArena Vision: English | Not measured | 1267 | Only Qwen3.8 27B measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only Qwen3.8 27B measured |
| LMArena Vision: reading text | Not measured | 1281 | Only Qwen3.8 27B measured |
| LMArena Vision: humor | Not measured | 1235 | Only Qwen3.8 27B measured |
| LMArena Vision: creative writing | Not measured | 1237 | Only Qwen3.8 27B measured |
| MultiChallenge | 67.7% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 5.5 | Qwen3.8 27B | 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 | Qwen3.8 27B |
|---|---|---|
| Maker | Anthropic | Qwen |
| Weights | No public weights listed | Open weights |
| Released | October 7, 2026 | August 14, 2026 |
| Context window | 1M | 1M |
| Input $/Mtok | $0.10 | $0.425 |
| Output $/Mtok | $0.50 | $2.55 |
| Coding index | 70.7 | 74.2 |
| Independent measurements behind it | 5 | 4 |
| Cost per solved task | Not computable | $1.26 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than Qwen3.8 27B for coding?
Pick Qwen3.8 27B for coding: it scores 74.2 on the Vibe Coding Index against 70.7 for Claude Haiku 5.5, though on 4 benchmarks against 5. Pick Claude Haiku 5.5 for output tokens 5.1x cheaper ($0.50 vs $2.55 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 Qwen3.8 27B?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen3.8 27B costs $0.425 and $2.55. Cost per solved task is known for Qwen3.8 27B only.
Which has the bigger context window, Claude Haiku 5.5 or Qwen3.8 27B?
Neither: both take 1M tokens.
How many benchmarks is the Claude Haiku 5.5 vs Qwen3.8 27B comparison based on?
34 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Qwen3.8 27B's on 4. Where only one model has a result, the page says so instead of naming a winner.