Claude Opus 4.5 vs Hy3 preview
Updated October 21, 2026. 34 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 Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 22.4 for Hy3 preview.
Pick Hy3 preview when output tokens cost 41.7x less, or when the context window is larger, 262K against 200K tokens.
- Shared results
- 34
- Claude Opus 4.5 only
- 71
- Hy3 preview only
- 2
- 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 Opus 4.5
Claude Opus 4.5 scores 66.8 against 22.4.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.5
Claude Opus 4.5 leads, 29.1 against 25.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Hy3 preview has a AA Agentic Index result, 24.1.
Directional only
Reasoning
GPQA Diamond
No call
Only Claude Opus 4.5 has a GPQA Diamond result, 85.9%.
Directional only
Math
AIME
No call
Only Claude Opus 4.5 has a AIME result, 95.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Opus 4.5 has a MMLU Pro result, 87.3%.
Directional only
Web design
Design Arena: websites
No call
Only Claude Opus 4.5 has a Design Arena: websites result, 1247.
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 Opus 4.5 $0.018, Hy3 preview $0.0005 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Opus 4.5 has the number, $1.37.
Directional only
At a glance
- Coding index
- Claude Opus 4.5 66.8 from 2 benchmarks, Hy3 preview 22.4 from 1 benchmark.
- Widest category
- Coding, 17.2 points apart on average over 6 shared benchmarks.
- Widest single gap
- LMArena WebDev: HTML: Claude Opus 4.5 1510 against Hy3 preview 1356, 25.7 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.5 $25.00 against Hy3 preview $0.60 per million output tokens, 41.7x apart.
- Context window
- Claude Opus 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 Opus 4.5 | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 4 | 1 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 14 | 1 | ||
| All shared boards | 31 | 3 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index60
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 79.2% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench (full test set) | 52.6% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Multilingual | 70.7% | Not measured | Only Claude Opus 4.5 measured |
| LMArena WebDev | 1494 | 1357 | Claude Opus 4.5 |
| AA Coding Index | Not measured | 58.8 | Only Hy3 preview measured |
| LiveCodeBench (Vals AI) | 83.7% | Not measured | Only Claude Opus 4.5 measured |
| SWE-bench Verified (Vals AI) | 76.4% | Not measured | Only Claude Opus 4.5 measured |
| Vibe Code Bench (Vals AI) | 20.6% | Not measured | Only Claude Opus 4.5 measured |
| LiveCodeBench (Artificial Analysis run) | 87.1% | Not measured | Only Claude Opus 4.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 34.1% | Claude Opus 4.5 |
| Terminal-Bench | 63.1% | Not measured | Only Claude Opus 4.5 measured |
| GSO-Bench | 26.5% | Not measured | Only Claude Opus 4.5 measured |
| WeirdML | 63.7% | Not measured | Only Claude Opus 4.5 measured |
| Cybench | 82.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: coding | 1503 | 1421 | Claude Opus 4.5 |
| LMArena Text: software and IT | 1483 | 1423 | Claude Opus 4.5 |
| LMArena WebDev: React | 1478 | 1349 | Claude Opus 4.5 |
| LMArena WebDev: HTML | 1510 | 1356 | Claude Opus 4.5 |
| Neither model has a result on the other 20 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.1 | 25.3 | Claude Opus 4.5 |
| Epoch Capabilities Index | 150.1 | Not measured | Only Claude Opus 4.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 24.1 | Only Hy3 preview measured |
| Design Arena: agents building web apps | 1159 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building full-stack apps | 1156 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building mobile apps | 1189 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: agents building Android apps | 1181 | Not measured | Only Claude Opus 4.5 measured |
| τ²-Bench Telecom | 89.5% | 92.7% | Hy3 preview |
| METR time horizons | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| Remote Labor Index | 3.8% | Not measured | Only Claude Opus 4.5 measured |
| GDPval | 45.5% | Not measured | Only Claude Opus 4.5 measured |
| BALROG | 43.5% | Not measured | Only Claude Opus 4.5 measured |
| DeepResearch Bench | 54.8% | Not measured | Only Claude Opus 4.5 measured |
| OSWorld | 66.3% | Not measured | Only Claude Opus 4.5 measured |
| Vending-Bench 2 | $4,967 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond | 85.9% | Not measured | Only Claude Opus 4.5 measured |
| MMMU Pro (Vals AI) | 83.0% | Not measured | Only Claude Opus 4.5 measured |
| GPQA Diamond (Artificial Analysis run) | 86.6% | 86.7% | Hy3 preview |
| Humanity's Last Exam (Artificial Analysis run) | 30.1% | 27.8% | Claude Opus 4.5 |
| GPQA Diamond (Epoch AI run) | 86.0% | Not measured | Only Claude Opus 4.5 measured |
| ARC-AGI | 80.0% | Not measured | Only Claude Opus 4.5 measured |
| ARC-AGI-2 | 37.6% | Not measured | Only Claude Opus 4.5 measured |
| SimpleBench | 62.0% | Not measured | Only Claude Opus 4.5 measured |
| Chess puzzles | 14.0% | Not measured | Only Claude Opus 4.5 measured |
| Mystery game puzzles | 22.0% | Not measured | Only Claude Opus 4.5 measured |
| EBR-bench | 14.3% | Not measured | Only Claude Opus 4.5 measured |
| VPCT | 40.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: hard prompts | 1476 | 1413 | Claude Opus 4.5 |
| LMArena Text: expert | 1487 | 1422 | Claude Opus 4.5 |
| LMArena Text: hard prompts in English | 1482 | 1416 | Claude Opus 4.5 |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| AIME | 95.4% | Not measured | Only Claude Opus 4.5 measured |
| MGSM (Vals AI) | 95.2% | Not measured | Only Claude Opus 4.5 measured |
| AA Math Index | 91.3 | Not measured | Only Claude Opus 4.5 measured |
| AIME 2025 (Artificial Analysis run) | 91.3% | Not measured | Only Claude Opus 4.5 measured |
| OTIS Mock AIME | 86.1% | Not measured | Only Claude Opus 4.5 measured |
| FrontierMath, tiers 1 to 3 | 34.4% | Not measured | Only Claude Opus 4.5 measured |
| FrontierMath, tier 4 | 4.9% | Not measured | Only Claude Opus 4.5 measured |
| ProofBench | 36.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: math | 1463 | 1424 | Claude Opus 4.5 |
| LMArena Text: mathematical work | 1468 | 1442 | Claude Opus 4.5 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | Not measured | Only Claude Opus 4.5 measured |
| LegalBench (Vals AI) | 84.6% | Not measured | Only Claude Opus 4.5 measured |
| CaseLaw (Vals AI) | 62.6% | Not measured | Only Claude Opus 4.5 measured |
| CorpFin (Vals AI) | 65.1% | Not measured | Only Claude Opus 4.5 measured |
| TaxEval (Vals AI) | 74.9% | Not measured | Only Claude Opus 4.5 measured |
| MortgageTax (Vals AI) | 68.7% | Not measured | Only Claude Opus 4.5 measured |
| MedQA (Vals AI) | 95.9% | Not measured | Only Claude Opus 4.5 measured |
| MedCode (Vals AI) | 49.2% | Not measured | Only Claude Opus 4.5 measured |
| MMLU Pro (Artificial Analysis run) | 89.5% | Not measured | Only Claude Opus 4.5 measured |
| SimpleQA Verified | 45.7% | Not measured | Only Claude Opus 4.5 measured |
| GeoBench | 75.0% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: science | 1454 | 1416 | Claude Opus 4.5 |
| LMArena Text: medicine and healthcare | 1444 | 1405 | Claude Opus 4.5 |
| LMArena Text: legal and government | 1459 | 1430 | Claude Opus 4.5 |
| LMArena Text: business and finance | 1448 | 1397 | Claude Opus 4.5 |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1247 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: UI components | 1238 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: game dev | 1229 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: data viz | 1243 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: 3D | 1214 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: all code categories | 1242 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: SVG | 1180 | Not measured | Only Claude Opus 4.5 measured |
| Design Arena: ASCII art | 1190 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index141
| Benchmark | Claude Opus 4.5 | Hy3 preview | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 52.1% | Not measured | Only Claude Opus 4.5 measured |
| MedScribe (Vals AI) | 85.3% | Not measured | Only Claude Opus 4.5 measured |
| IFBench | 58.0% | 63.1% | Hy3 preview |
| Long context reasoning (AA-LCR) | 77.3% | 64.7% | Claude Opus 4.5 |
| DTBench | 89.9% | Not measured | Only Claude Opus 4.5 measured |
| LMCA | 44.5% | Not measured | Only Claude Opus 4.5 measured |
| CL-bench | 21.1% | Not measured | Only Claude Opus 4.5 measured |
| Furniture assembly | 28.3% | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text | 1451 | 1401 | Claude Opus 4.5 |
| LMArena Text: instruction following | 1478 | 1383 | Claude Opus 4.5 |
| LMArena Text: creative writing | 1445 | 1339 | Claude Opus 4.5 |
| LMArena Text: English | 1461 | 1409 | Claude Opus 4.5 |
| LMArena Text: non-English | 1438 | 1390 | Claude Opus 4.5 |
| LMArena Text: Chinese | 1470 | 1435 | Claude Opus 4.5 |
| LMArena Text: German | 1449 | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: Japanese | 1417 | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: Korean | 1424 | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: French | 1471 | 1425 | Claude Opus 4.5 |
| LMArena Text: Spanish | 1457 | 1399 | Claude Opus 4.5 |
| LMArena Text: Russian | 1447 | 1399 | Claude Opus 4.5 |
| LMArena Text: Polish | 1439 | Not measured | Only Claude Opus 4.5 measured |
| LMArena Text: multi-turn | 1466 | 1411 | Claude Opus 4.5 |
| LMArena Text: longer queries | 1479 | 1402 | Claude Opus 4.5 |
| LMArena Text: writing and language | 1452 | 1370 | Claude Opus 4.5 |
| LMArena Text: entertainment and media | 1434 | 1352 | Claude Opus 4.5 |
| LMArena Document | 1462 | Not measured | Only Claude Opus 4.5 measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 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 Opus 4.5 | Tencent Hy3 preview |
|---|---|---|
| Maker | Anthropic | Tencent |
| Weights | No public weights listed | Open weights |
| Released | November 24, 2025 | April 22, 2026 |
| Context window | 200K | 262K |
| Input $/Mtok | $5.00 | $0.18 |
| Output $/Mtok | $25.00 | $0.60 |
| Coding index | 66.8 | 22.4 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $1.37 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.5 better than Hy3 preview for coding?
Pick Claude Opus 4.5 for coding: it scores 66.8 on the Vibe Coding Index against 22.4 for Hy3 preview. Pick Hy3 preview when output tokens cost 41.7x less, or when the context window is larger, 262K against 200K tokens.
Which is cheaper, Claude Opus 4.5 or Hy3 preview?
Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for Claude Opus 4.5 only.
Which has the bigger context window, Claude Opus 4.5 or Hy3 preview?
Hy3 preview, with 262K tokens against 200K.
How many benchmarks is the Claude Opus 4.5 vs Hy3 preview comparison based on?
34 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.5's coding index rests on 2 independent benchmarks and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.