Claude Opus 5.5
Anthropic · released Sep 22, 2026
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Specification
- Context window
- 1M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 5
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
57.6
100th percentile
Coding
—
Coding Index
Agentic
—
Agentic Index
Output speed
174 t/s
Median across providers
Latency
2.28s
Time to first token
Cost per task
$1.80
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- AA-LCR (long context)84.7%
- SciCode66.9%
- Humanity's Last Exam61.4%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| AA-LCR (long context) | 84.7% |
| SciCode | 66.9% |
| Humanity's Last Exam | 61.4% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Qwen3.8 MaxQwen58.1
- Claude Opus 5.5Anthropic57.6
- Claude Sonnet 5.5Anthropic56.0
- Claude Fable 5.1Anthropic53.4
- GPT-6 AstraOpenAI52.7
- Gemini 4 ArgonGoogle52.6
- Muse WonderMeta52.4
- GPT-6.1 SolOpenAI51.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Qwen3.8 Max | 58.1 |
| Claude Opus 5.5 | 57.6 |
| Claude Sonnet 5.5 | 56.0 |
| Claude Fable 5.1 | 53.4 |
| GPT-6 Astra | 52.7 |
| Gemini 4 Argon | 52.6 |
| Muse Wonder | 52.4 |
| GPT-6.1 Sol | 51.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $4
- Output / 1M tokens
- $20
- Cached input / 1M
- $0.2
- Blended 3:1
- $8
One task, estimated
$1.80
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,479
- Win rate
- 72.1%
- Strongest at
- 3D scenes
- Tournaments
- 831
Elo by category
Dot position on a 1,325–1,500 scale · Elo has no meaningful zero
- 1,479
- 1,459
- 1,400
- 1,380
- 1,337
- 1,332
- 1,327
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| 3D scenes | 1479 | 72.1% |
| Game development | 1459 | 71.8% |
| Data visualisation | 1400 | 64.8% |
| UI components | 1380 | 63.3% |
| Websites | 1337 | 57.5% |
| SVG | 1332 | 51.8% |
| Mobile apps | 1327 | 64.2% |