text model comparison
Claude Opus 5.5 vs Hy4
Claude Opus 5.5 and Hy4 are both current text models, from Anthropic and Tencent. Hy4 is 79% cheaper per 1M input tokens than Claude Opus 5.5, $0.834 vs $4. In Tencent's Hy4 launch table, Claude Opus 5.5 scores 72.6% on DeepSWE v1.1 and Hy4 74.9%.
- Lower price per 1M input tokens
- Hy4$0.834 against $4
- Newer release
- Hy4Nov 2026 against Sep 2026
Data verified November 5, 2026 · Dataset 2026-11-05
Side by side
Claude Opus 5.5 and Hy4, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Claude Opus 5.5 | Hy4 |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $4 | $0.834 (better) |
| Price per 1M output tokens | $20 | $2.501 (better) |
| Independent benchmarks | ||
| Arena Text | 1509 Elo (#3 of 52) | Not measured |
| Arena WebDev | 1810 Elo (#1 of 46) | Not measured |
| GPQA Diamond | 90.6% (#25 of 41) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 91.2% (#3 of 41) | Not measured |
| SimpleQA Verified | 72.2% (#5 of 38) | Not measured |
| Specs | ||
| Provider | Anthropic | Tencent |
| Release date | September 22, 2026 | November 4, 2026 |
| Access | API only | API only |
| Context window | 1,000,000 tokens | Not reported |
| Max output | 128,000 tokens | Not reported |
| Input | text, image | text, image |
| Output | text | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both Claude Opus 5.5 and Hy4. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.
Tencent, Hy4 launch table, November 4, 2026Tencent · 2026-11-05
| Benchmark | Claude Opus 5.5 | Hy4 |
|---|---|---|
| DeepSWE v1.1 | 72.6% | 74.9% (better) |
| SWE-Marathon v1.1 | 44.4% (better) | 43.8% |
| ProgramBenchalmost solved | 56.5% (better) | 30.0% |
| Terminal-Bench 4.0 | 66.4% (better) | 44.4% |
| FrontierCode 2.0 | 46.4% (better) | 31.0% |
| APEX-Agents v1.1pass@1 | 74.8% | 75.2% (better) |
| Agents' Last Exam v1.1pass rate | 43.4% (better) | 41.0% |
| AutomationBench v1.0.6 | 58.8% (better) | 56.2% |
| HLE-Fullwith tools | 66.2% (better) | 59.1% |
| Terminal-Bench-Science 0.1 | 56.2% (better) | 19.8% |
| PostTrainBench v1.2 | 44.2% (better) | 35.2% |
| OSWorld 2.1full, partial score | 81.8% (better) | 78.9% |
| MMMU-Pro | 88.2% (better) | 78.6% |
| ZeroBench mainwith tools, pass@5 | 63.5% (better) | 55.4% |
Tencent's appendix to the Hy4 announcement, every model at its highest reasoning setting. Where Tencent lists a lab's reported score beside its own run, the score Tencent measured is shown. DeepSeek-V4.1-Flash is the 1017 build. Left out here: Tencent's internal benchmarks, the Hy4 preview column and GLM-5.3 on HLE, which Tencent ran on the text-only subset.
Charts
Against every current text model
Where Claude Opus 5.5 and Hy4 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only Claude Opus 5.5 has a current Arena Text score: #3 of 52. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text
Claude Opus 5.5:#3of 52
1,509 Elo · ahead of 96%
Hy4: Not scored
Arena WebDev
Claude Opus 5.5:#1of 46
1,810 Elo · ahead of 100%
Hy4: Not scored
GPQA Diamond
Claude Opus 5.5:#25of 41
90.6% · ahead of 40%
Hy4: Not scored
FrontierMath Tiers 1-3 (v2)
Claude Opus 5.5:#3of 41
91.2% · ahead of 95%
Hy4: Not scored
SimpleQA Verified
Claude Opus 5.5:#5of 38
72.2% · ahead of 89%
Hy4: Not scored
Price and context
Price per 1M input tokens
Claude Opus 5.5:#45of 55
$4 · cheaper than 15%
Hy4:#21of 55
$0.834 · cheaper than 63%
Price per 1M output tokens
Claude Opus 5.5:#45of 55
$20 · cheaper than 15%
Hy4:#20of 55
$2.501 · cheaper than 65%
Context window
Claude Opus 5.5:#26of 64
1M tokens · longer than 22%
Hy4: Not listed
Quality against price
Claude Opus 5.5 scores 1,509 at $8 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Carbon | $4 | 1,528 | |
| Gemini 4 Argon | $4 | 1,520 | |
| Claude Opus 5.5 | Anthropic | $8 | 1,509 |
| Muse Wonder | Meta | $8 | 1,507 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,504 |
| Gemini 3.8 Flash | $1.50 | 1,496 | |
| Muse Spark 1.3 | Meta | $2 | 1,495 |
| Claude Opus 5 | Anthropic | $10 | 1,492 |
| Kimi K3 | Moonshot Kimi | $6 | 1,488 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GPT-5.5 | OpenAI | $11 | 1,482 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,481 |
| GLM-5.3 | Z.ai | $2.15 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,477 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,477 |
| GPT-6 Astra | OpenAI | $20 | 1,476 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,476 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,467 |
| Grok 4.5 | xAI | $3 | 1,465 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,465 |
| Claude Sonnet 5 | Anthropic | $4 | 1,462 |
| GPT-6 Sol | OpenAI | $4 | 1,458 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,456 | |
| Grok 4.6 | xAI | $3 | 1,455 |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Grok 4.7 | xAI | $3 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,432 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,425 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Solar Pro 4 | Upstage | $0.52 | 1,388 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, Claude Opus 5.5 costs 6.0 times as much as Hy4, at each provider's listed rates.
10M input and 2M output tokens
Claude Opus 5.5 costs 6.0× as much
- Claude Opus 5.5
- $80
- Hy4
- $13.34
The same, with 9M of the input tokens cached
Claude Opus 5.5 costs 7.4× as much
- Claude Opus 5.5
- $45.80
- Hy4
- $6.21
| Workload or rate | Claude Opus 5.5 | Hy4 |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $80 | $13.34 (better) |
| The same, with 9M of the input tokens cached | $45.80 | $6.21 (better) |
| The same, through the batch API | $40 | Not listed |
| Other listed rates | ||
| 1M input tokens, cached | $0.20 | $0.042 (better) |
| 1M input tokens, 5-minute cache write | $5 | Not listed |
| 1M input tokens, 1-hour cache write | $8 | Not listed |
| 1M input tokens, batch | $2 | Not listed |
| 1M output tokens, batch | $10 | Not listed |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Claude Opus 5.5
Where it leads
- Batch pricing, $2 input and $10 output per 1M tokens
Best for
- Long-running agentic coding and knowledge work as the general-purpose default
- Cache-heavy agent loops where the 0.05x read multiplier compounds
Watch out for
- The API effort default is medium here, not high as on Claude Fable 5.1 and Claude Sonnet 5.5, so a like-for-like comparison has to set effort explicitly
- The 4.7-generation tokenizer produces roughly 30% more tokens for the same text than Claude Sonnet 4.6 and earlier, so per-token rates do not compare directly across generations
Hy4
Where it leads
- Lower input and output prices, $0.834 and $2.501 vs $4 and $20 per 1M tokens
- Cheaper cached input, $0.042 vs $0.20 per 1M tokens
Best for
- Agents that work across terminals, desktop apps and browsers on a tight budget
- Finance and office work: research reports, spreadsheets and slides
Watch out for
- API only for now: Tencent says it will publish the weights and a system card later, and only Hy4 preview (August 2026, Apache 2.0) is open today
- In Tencent's own table it scores 44.4% on Terminal-Bench 4.0 against 66.8% for Kimi K3.1 Pro, and Tencent says a clear gap remains to top proprietary models on research-level math, long-horizon coding and hard visual questions
- Tencent publishes no context window or output limit for Hy4 (the preview card lists 1M tokens), and no independent benchmark score is recorded here yet
From benchmark to production
Building on Claude Opus 5.5 or Hy4?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
Claude Opus 5.5 vs Hy4 FAQ
Which is cheaper, Claude Opus 5.5 or Hy4?
Hy4 is 79% cheaper per 1M input tokens than Claude Opus 5.5, $0.834 vs $4. For 10M input and 2M output tokens, Claude Opus 5.5 costs $80 and Hy4 $13.34 at standard rates.
Which is cheaper with prompt caching, Claude Opus 5.5 or Hy4?
Claude Opus 5.5 charges $0.20 per 1M cached input tokens, 95% below its standard input rate, and Hy4 $0.042, 95% below. With 9M of 10M input tokens cached and 2M output tokens, Claude Opus 5.5 costs $45.80 and Hy4 $6.21.
How do Claude Opus 5.5 and Hy4 compare in Tencent's own results?
In Hy4 launch table (November 4, 2026), Hy4 leads on DeepSWE v1.1, 74.9% to 72.6%; Claude Opus 5.5 leads on SWE-Marathon v1.1, 44.4% to 43.8%; Claude Opus 5.5 leads on ProgramBench (almost solved), 56.5% to 30.0%. These are Tencent's figures, not independent measurements.
Further reading
More on Claude Opus 5.5 and Hy4
Articles on Claude Opus 5.5 and Hy4
- GDPval-AA Chart Fact-Check: Opus 5.5 vs GPT-6 Astra on CostSeptember 24, 2026
- GPT-6 Sol vs Claude Opus 5.5, Plus Luna: Best Value per TaskSeptember 24, 2026
- Claude Opus 5.5 Benchmarks: What the Chart Shows and HidesSeptember 23, 2026
- Claude Opus 5.5: Tops the Independent Index at a Lower PriceSeptember 23, 2026
Related comparisons
- Claude Haiku 5.5 vs Claude Opus 5.5
- DeepSeek-V4.1-Flash vs Hy4
- Claude Opus 5.5 vs Gemini 4 Argon
- Gemini 3.8 Flash vs Hy4
- Claude Opus 5.5 vs GPT-6.1 Sol
- GLM-5.3-Flash vs Hy4
- Claude Opus 5.5 vs Claude Sonnet 5.5
- GLM-5.3 vs Hy4
- Claude Fable 5 vs Claude Opus 5.5
- GPT-6.1 Sol vs Hy4
- Claude Opus 4.8 vs Claude Opus 5.5
- GPT-6.1 Terra vs Hy4
Production evaluation
Choosing between Claude Opus 5.5 and Hy4?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty