Claude Opus 5
Anthropic · released Jul 24, 2026
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
Specification
- Context window
- 1M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 5
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
50.8
98th percentile
Coding
78.0
Coding Index
Agentic
56.5
Agentic Index
Output speed
98 t/s
Median across providers
Latency
1.39s
Time to first token
Cost per task
$2.25
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
- GPQA Diamond93.2%
- AA-LCR (long context)79.3%
- SciCode56.4%
- Humanity's Last Exam54.9%
- τ²-bench (Telecom)42.1%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 93.2% |
| AA-LCR (long context) | 79.3% |
| SciCode | 56.4% |
| Humanity's Last Exam | 54.9% |
| τ²-bench (Telecom) | 42.1% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Fable 5.1Anthropic53.4
- GPT-6 AstraOpenAI52.7
- Gemini 4 ArgonGoogle52.6
- Muse WonderMeta52.4
- GPT-6.1 SolOpenAI51.8
- Claude Opus 5Anthropic50.8
- Claude Fable 5Anthropic49.6
- Muse Spark 1.3Meta48.1
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| 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 |
| Claude Opus 5 | 50.8 |
| Claude Fable 5 | 49.6 |
| Muse Spark 1.3 | 48.1 |
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
- $5
- Output / 1M tokens
- $25
- Cached input / 1M
- $0.5
- Blended 3:1
- $10
One task, estimated
$2.25
- 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
- 1,349
- Win rate
- 60.7%
- Strongest at
- UI components
- Tournaments
- 1,584
Elo by category
Dot position on a 1,300–1,350 scale · Elo has no meaningful zero
- 1,349
- 1,340
- 1,335
- 1,329
- 1,310
- 1,310
- 1,306
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| UI components | 1349 | 60.7% |
| Game development | 1340 | 58.4% |
| 3D scenes | 1335 | 59.7% |
| Data visualisation | 1329 | 58.2% |
| Websites | 1310 | 55.8% |
| SVG | 1310 | 58.4% |
| Full-stack apps | 1306 | 57.3% |