Claude Haiku 4.5 vs Hy3 preview
Updated October 21, 2026. 30 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 22.4 for Hy3 preview.
Pick Hy3 preview when output tokens cost 8.3x less, or when the context window is larger, 262K against 200K tokens.
- Shared results
- 30
- Claude Haiku 4.5 only
- 64
- Hy3 preview only
- 6
- Like-for-like categories
- 7 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
Claude Haiku 4.5
Claude Haiku 4.5 scores 49.8 against 22.4.
3 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
Hy3 preview
Hy3 preview leads, 24.1 against 8.0.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Claude Haiku 4.5 has a GPQA Diamond result, 72.2%.
Directional only
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Haiku 4.5 has a MMLU Pro result, 78.7%.
Directional only
Web design
Design Arena: websites
No call
Only Claude Haiku 4.5 has a Design Arena: websites result, 1122.
Directional only
Long documents
Listed context window
Hy3 preview
Hy3 preview takes 262K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3 preview
Claude Haiku 4.5 $0.0035, Hy3 preview $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Haiku 4.5 has the number, $0.56.
Directional only
At a glance
- Coding index
- Claude Haiku 4.5 49.8 from 3 benchmarks, Hy3 preview 22.4 from 1 benchmark.
- Widest category
- Agentic work, 16.1 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Agentic Index: Claude Haiku 4.5 8.0 against Hy3 preview 24.1, 16.1 points apart on a 0 to 100 scale.
- Output price
- Claude Haiku 4.5 $5.00 against Hy3 preview $0.60 per million output tokens, 8.3x apart.
- Context window
- Claude Haiku 4.5 takes 200K tokens, Hy3 preview 262K.
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 4.5 | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 2 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 3 | 0 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 3 | ||
| General | 7 | 6 | ||
| All shared boards | 13 | 17 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index24
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Multilingual | 64.7% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench coding | 48.1% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena WebDev | 1330 | 1357 | Hy3 preview |
| AA Coding Index | 43.9 | 58.8 | Hy3 preview |
| LiveCodeBench (Vals AI) | 41.2% | Not measured | Only Claude Haiku 4.5 measured |
| SWE-bench Verified (Vals AI) | 66.6% | Not measured | Only Claude Haiku 4.5 measured |
| Vibe Code Bench (Vals AI) | 11.4% | Not measured | Only Claude Haiku 4.5 measured |
| Code migration (Vals AI) | 7.5% | Not measured | Only Claude Haiku 4.5 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 43.8% | Not measured | Only Claude Haiku 4.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.1% | Only Hy3 preview measured |
| Terminal-Bench | 35.5% | Not measured | Only Claude Haiku 4.5 measured |
| WeirdML | 45.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: coding | 1454 | 1421 | Claude Haiku 4.5 |
| LMArena Text: software and IT | 1439 | 1423 | Claude Haiku 4.5 |
| LMArena WebDev: React | 1326 | 1349 | Hy3 preview |
| LMArena WebDev: HTML | 1318 | 1356 | Hy3 preview |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.9 | 25.3 | Hy3 preview |
| Epoch Capabilities Index | 142.2 | Not measured | Only Claude Haiku 4.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | 8.0 | 24.1 | Hy3 preview |
| LiveBench research | 42.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench browser | 40.0% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench long agentic | 11.1% | Not measured | Only Claude Haiku 4.5 measured |
| Finance Agent (Vals AI) | 31.0% | Not measured | Only Claude Haiku 4.5 measured |
| Tax Agent Bench (Vals AI) | 5.9% | Not measured | Only Claude Haiku 4.5 measured |
| Legal Research Bench (Vals AI) | 10.6% | Not measured | Only Claude Haiku 4.5 measured |
| Excel Modeling Benchmark (Vals AI) | 22.7% | Not measured | Only Claude Haiku 4.5 measured |
| τ²-Bench Telecom | Not measured | 92.7% | Only Hy3 preview measured |
| BALROG | 31.2% | Not measured | Only Claude Haiku 4.5 measured |
| DeepResearch Bench | 45.5% | Not measured | Only Claude Haiku 4.5 measured |
| Vending-Bench 2 | $459 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench reasoning | 61.7% | Not measured | Only Claude Haiku 4.5 measured |
| MMMU Pro (Vals AI) | 46.1% | Not measured | Only Claude Haiku 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 86.7% | Only Hy3 preview measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 27.8% | Only Hy3 preview measured |
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI | 47.7% | Not measured | Only Claude Haiku 4.5 measured |
| ARC-AGI-2 | 4.0% | Not measured | Only Claude Haiku 4.5 measured |
| Chess puzzles | 8.0% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: hard prompts | 1421 | 1413 | Claude Haiku 4.5 |
| LMArena Text: expert | 1443 | 1422 | Claude Haiku 4.5 |
| LMArena Text: hard prompts in English | 1435 | 1416 | Claude Haiku 4.5 |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AIME | 82.7% | Not measured | Only Claude Haiku 4.5 measured |
| MGSM (Vals AI) | 92.2% | Not measured | Only Claude Haiku 4.5 measured |
| OTIS Mock AIME | 66.7% | Not measured | Only Claude Haiku 4.5 measured |
| MATH level 5 | 96.4% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: math | 1398 | 1424 | Hy3 preview |
| LMArena Text: mathematical work | 1430 | 1442 | Hy3 preview |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| MMLU Pro | 78.7% | Not measured | Only Claude Haiku 4.5 measured |
| LegalBench (Vals AI) | 81.2% | Not measured | Only Claude Haiku 4.5 measured |
| CaseLaw (Vals AI) | 56.5% | Not measured | Only Claude Haiku 4.5 measured |
| CorpFin (Vals AI) | 60.6% | Not measured | Only Claude Haiku 4.5 measured |
| TaxEval (Vals AI) | 67.5% | Not measured | Only Claude Haiku 4.5 measured |
| MortgageTax (Vals AI) | 62.2% | Not measured | Only Claude Haiku 4.5 measured |
| MedQA (Vals AI) | 79.6% | Not measured | Only Claude Haiku 4.5 measured |
| MedCode (Vals AI) | 32.7% | Not measured | Only Claude Haiku 4.5 measured |
| SimpleQA Verified | 13.2% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: science | 1406 | 1416 | Hy3 preview |
| LMArena Text: medicine and healthcare | 1394 | 1405 | Hy3 preview |
| LMArena Text: legal and government | 1400 | 1430 | Hy3 preview |
| LMArena Text: business and finance | 1400 | 1397 | Claude Haiku 4.5 |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1122 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: UI components | 1100 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: game dev | 1097 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: data viz | 1124 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: 3D | 1072 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: all code categories | 1115 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: SVG | 1025 | Not measured | Only Claude Haiku 4.5 measured |
| Design Arena: ASCII art | 1139 | Not measured | Only Claude Haiku 4.5 measured |
| LiveBench design | 59.9% | Not measured | Only Claude Haiku 4.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index76
| Benchmark | Claude Haiku 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| LiveBench data analysis | 59.3% | Not measured | Only Claude Haiku 4.5 measured |
| Public Benefits Bench (Vals AI) | 54.3% | Not measured | Only Claude Haiku 4.5 measured |
| SAGE (Vals AI) | 31.8% | Not measured | Only Claude Haiku 4.5 measured |
| MedScribe (Vals AI) | 85.2% | Not measured | Only Claude Haiku 4.5 measured |
| Vals Multimodal Index | 42.9% | Not measured | Only Claude Haiku 4.5 measured |
| IFBench | Not measured | 63.1% | Only Hy3 preview measured |
| Long context reasoning (AA-LCR) | Not measured | 64.7% | Only Hy3 preview measured |
| DTBench | 73.6% | Not measured | Only Claude Haiku 4.5 measured |
| LMCA | 30.9% | Not measured | Only Claude Haiku 4.5 measured |
| ExploitBench | 13.7% | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text | 1397 | 1401 | Hy3 preview |
| LMArena Text: instruction following | 1414 | 1383 | Claude Haiku 4.5 |
| LMArena Text: creative writing | 1371 | 1339 | Claude Haiku 4.5 |
| LMArena Text: English | 1414 | 1409 | Claude Haiku 4.5 |
| LMArena Text: non-English | 1377 | 1390 | Hy3 preview |
| LMArena Text: Chinese | 1418 | 1435 | Hy3 preview |
| LMArena Text: German | 1374 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Japanese | 1338 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: Korean | 1346 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: French | 1411 | 1425 | Hy3 preview |
| LMArena Text: Spanish | 1421 | 1399 | Claude Haiku 4.5 |
| LMArena Text: Russian | 1381 | 1399 | Hy3 preview |
| LMArena Text: Polish | 1343 | Not measured | Only Claude Haiku 4.5 measured |
| LMArena Text: multi-turn | 1409 | 1411 | Hy3 preview |
| LMArena Text: longer queries | 1427 | 1402 | Claude Haiku 4.5 |
| LMArena Text: writing and language | 1386 | 1370 | Claude Haiku 4.5 |
| LMArena Text: entertainment and media | 1369 | 1352 | Claude Haiku 4.5 |
| LMArena Document | 1420 | Not measured | Only Claude Haiku 4.5 measured |
| Neither model has a result on the other 18 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Haiku 4.5 | Hy3 preview | 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
Hy3 preview costs less
Repository review
50K input + 3K output tokens
Hy3 preview costs less
Agent loop
200K input + 10K output tokens
Hy3 preview 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 4.5 | Tencent Hy3 preview |
|---|---|---|
| Maker | Anthropic | Tencent |
| Weights | No public weights listed | Open weights |
| Released | October 15, 2025 | April 22, 2026 |
| Context window | 200K | 262K |
| Input $/Mtok | $1.00 | $0.18 |
| Output $/Mtok | $5.00 | $0.60 |
| Coding index | 49.8 | 22.4 |
| Independent measurements behind it | 3 | 1 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Haiku 4.5 better than Hy3 preview for coding?
Pick Claude Haiku 4.5 for coding: it scores 49.8 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when output tokens cost 8.3x less, or when the context window is larger, 262K against 200K tokens.
Which is cheaper, Claude Haiku 4.5 or Hy3 preview?
Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for Claude Haiku 4.5 only.
Which has the bigger context window, Claude Haiku 4.5 or Hy3 preview?
Hy3 preview, with 262K tokens against 200K.
How many benchmarks is the Claude Haiku 4.5 vs Hy3 preview comparison based on?
30 benchmarks have a result for both models as of October 21, 2026. Claude Haiku 4.5's coding index rests on 3 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.