Claude Haiku 5.5 vs Qwen3 235B A22B Thinking 2507
Claude Haiku 5.5 leads Qwen3 235B A22B Thinking 2507 on the Artificial Analysis Intelligence Index, 43.4 to 12.7, and Claude Haiku 5.5 costs 7.0x less per output token ($0.50 vs $3.50 per million). Updated October 23, 2026; 37 benchmarks have a result for both.
Claude Haiku 5.5 or Qwen3 235B A22B Thinking 2507: which to pick
Only Claude Haiku 5.5 has a coding score, 70.7 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: expert or LMArena Text: hard prompts in English, where it leads.
- Shared results
- 37
- Claude Haiku 5.5 only
- 52
- Qwen3 235B A22B Thinking 2507 only
- 9
- 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
No call
Only Claude Haiku 5.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Claude Haiku 5.5
Claude Haiku 5.5 leads, 43.4 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
Claude Haiku 5.5
Claude Haiku 5.5 leads, 1262 against 1052.
Same board, both measured
General
Vals Index
No call
Only Claude Haiku 5.5 has a Vals Index result, 58.7%.
Directional only
Long documents
Listed context window
Claude Haiku 5.5
Claude Haiku 5.5 takes 1M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 $0.0003, Qwen3 235B A22B Thinking 2507 $0.0022 per turn.
List prices
At a glance
- Coding index
- Claude Haiku 5.5 70.7 from 5 benchmarks, Qwen3 235B A22B Thinking 2507 not benchmarked.
- Widest category
- Web design, 38.4 points apart on average over 6 shared benchmarks.
- Widest single gap
- Design Arena: game dev: Claude Haiku 5.5 1315 against Qwen3 235B A22B Thinking 2507 956, 44.9 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 5.5 $0.50 against Qwen3 235B A22B Thinking 2507 $3.50 per million output tokens, 7.0x apart.
- Context window
- Claude Haiku 5.5 takes 1M tokens, Qwen3 235B A22B Thinking 2507 128K.
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 235B A22B Thinking 2507 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 2 | ||
| Math | 2 | 1 | ||
| Knowledge | 0 | 5 | ||
| Web design | 6 | 0 | ||
| General | 3 | 11 | ||
| All shared boards | 18 | 19 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| LiveBench coding | 91.4% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev | 1585 | Not measured | Only Claude Haiku 5.5 measured |
| AA Coding Index | Not measured | 22.1 | Only Qwen3 235B A22B Thinking 2507 measured |
| Terminal-Bench 4 (Vals AI) | 36.4% | Not measured | Only Claude Haiku 5.5 measured |
| Vibe Code Bench (Vals AI) | 90.4% | Not measured | Only Claude Haiku 5.5 measured |
| 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 |
| FrontierCode | 46.4% | Not measured | Only Claude Haiku 5.5 measured |
| FrontierSWE | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| WeirdML | Not measured | 41.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: coding | 1450 | 1424 | Claude Haiku 5.5 |
| LMArena Text: software and IT | 1446 | 1431 | Claude Haiku 5.5 |
| LMArena WebDev: React | 1606 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena WebDev: HTML | 1565 | Not measured | Only Claude Haiku 5.5 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 22 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Intelligence Index | 43.4 | 12.7 | Claude Haiku 5.5 |
| Epoch Capabilities Index | 159.3 | Not measured | Only Claude Haiku 5.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 1.3 | Only Qwen3 235B A22B Thinking 2507 measured |
| LiveBench research | 81.9% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench browser | 80.0% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench long agentic | 57.6% | Not measured | Only Claude Haiku 5.5 measured |
| 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% | Not measured | Only Claude Haiku 5.5 measured |
| Legal Research Bench (Vals AI) | 43.3% | Not measured | Only Claude Haiku 5.5 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | Not measured | Only Claude Haiku 5.5 measured |
| 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 | -$11 | Claude Haiku 5.5 |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| LiveBench reasoning | 82.4% | Not measured | Only Claude Haiku 5.5 measured |
| 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 |
| GPQA Diamond (Epoch AI run) | 89.6% | 80.1% | Claude Haiku 5.5 |
| 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 |
| Chess puzzles | 55.0% | Not measured | Only Claude Haiku 5.5 measured |
| Mystery game puzzles | 30.0% | 9.0% | Claude Haiku 5.5 |
| EBR-bench | 43.8% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: hard prompts | 1421 | 1416 | Claude Haiku 5.5 |
| LMArena Text: expert | 1448 | 1463 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: hard prompts in English | 1429 | 1432 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| OTIS Mock AIME | 98.9% | 86.7% | Claude Haiku 5.5 |
| 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 | 1413 | 1412 | Claude Haiku 5.5 |
| LMArena Text: mathematical work | 1431 | 1435 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 8 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| MedCode (Vals AI) | 51.5% | Not measured | Only Claude Haiku 5.5 measured |
| SimpleQA Verified | 23.8% | 40.4% | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: science | 1408 | 1433 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: medicine and healthcare | 1372 | 1456 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: legal and government | 1395 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: business and finance | 1406 | 1412 | Qwen3 235B A22B Thinking 2507 |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| Design Arena: websites | 1262 | 1052 | Claude Haiku 5.5 |
| Design Arena: UI components | 1282 | 942 | Claude Haiku 5.5 |
| Design Arena: game dev | 1315 | 956 | Claude Haiku 5.5 |
| Design Arena: data viz | 1293 | 950 | Claude Haiku 5.5 |
| Design Arena: 3D | 1342 | 998 | Claude Haiku 5.5 |
| Design Arena: all code categories | 1277 | 1032 | Claude Haiku 5.5 |
| LiveBench design | 83.1% | Not measured | Only Claude Haiku 5.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index311
| Benchmark | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | Leader |
|---|---|---|---|
| Vals Index | 58.7% | Not measured | Only Claude Haiku 5.5 measured |
| LiveBench data analysis | 53.1% | Not measured | Only Claude Haiku 5.5 measured |
| Public Benefits Bench (Vals AI) | 63.2% | Not measured | Only Claude Haiku 5.5 measured |
| SAGE (Vals AI) | 45.8% | 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 |
| DTBench | 95.0% | 80.3% | Claude Haiku 5.5 |
| LMCA | 51.1% | 29.3% | Claude Haiku 5.5 |
| Fiction.LiveBench | Not measured | 75.0% | Only Qwen3 235B A22B Thinking 2507 measured |
| Creative writing (Lech Mazur) | Not measured | 82.4% | Only Qwen3 235B A22B Thinking 2507 measured |
| Furniture assembly | 47.5% | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text | 1401 | 1415 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: instruction following | 1416 | 1386 | Claude Haiku 5.5 |
| LMArena Text: creative writing | 1336 | 1384 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: English | 1409 | 1429 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: non-English | 1386 | 1397 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Chinese | 1431 | 1481 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: German | Not measured | 1408 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Japanese | Not measured | 1386 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: Korean | Not measured | 1375 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: French | 1441 | Not measured | Only Claude Haiku 5.5 measured |
| LMArena Text: Spanish | 1385 | 1389 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Russian | 1373 | 1400 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: Polish | Not measured | 1390 | Only Qwen3 235B A22B Thinking 2507 measured |
| LMArena Text: multi-turn | 1396 | 1406 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: longer queries | 1399 | 1399 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: writing and language | 1370 | 1388 | Qwen3 235B A22B Thinking 2507 |
| LMArena Text: entertainment and media | 1352 | 1370 | Qwen3 235B A22B Thinking 2507 |
| MultiChallenge | 67.7% | Not measured | Only Claude Haiku 5.5 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 | Claude Haiku 5.5 | Qwen3 235B A22B Thinking 2507 | 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 235B A22B Thinking 2507 |
|---|---|---|
| Maker | Anthropic | Qwen |
| Weights | No public weights listed | Open weights |
| Released | October 7, 2026 | July 25, 2025 |
| Context window | 1M | 128K |
| Input $/Mtok | $0.10 | $0.45 |
| Output $/Mtok | $0.50 | $3.50 |
| Coding index | 70.7 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 5.5 better than Qwen3 235B A22B Thinking 2507 for coding?
Only Claude Haiku 5.5 has a coding score, 70.7 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: expert or LMArena Text: hard prompts in English, where it leads.
Which is cheaper, Claude Haiku 5.5 or Qwen3 235B A22B Thinking 2507?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens; Qwen3 235B A22B Thinking 2507 costs $0.45 and $3.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Claude Haiku 5.5 or Qwen3 235B A22B Thinking 2507?
Claude Haiku 5.5, with 1M tokens against 128K.
How many benchmarks is the Claude Haiku 5.5 vs Qwen3 235B A22B Thinking 2507 comparison based on?
37 benchmarks have a result for both models as of October 23, 2026. Claude Haiku 5.5's coding index rests on 5 independent benchmarks and Qwen3 235B A22B Thinking 2507's on 0. Where only one model has a result, the page says so instead of naming a winner.