Claude Sonnet 5
Anthropic · released Jun 30, 2026
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
Specification
- Context window
- 1M
- Max output
- 128K
- Knowledge cutoff
- Not stated
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 4
- Moderated
- Yes
- Uptime
- 100.0%
Intelligence
55.3
97th percentile
Coding
71.5
Coding Index
Agentic
49.7
Agentic Index
Output speed
102 t/s
Median across providers
Latency
1.39s
Time to first token
Cost per task
$0.90
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 Diamond91.1%
- AA-LCR (long context)77.0%
- SciCode53.6%
- Humanity's Last Exam41.3%
- τ²-bench (Telecom)37.3%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 91.1% |
| AA-LCR (long context) | 77.0% |
| SciCode | 53.6% |
| Humanity's Last Exam | 41.3% |
| τ²-bench (Telecom) | 37.3% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- Claude Opus 4.8Anthropic57.3
- Muse Spark 1.2Meta56.8
- GPT-5.6 TerraOpenAI56.6
- GPT-5.5OpenAI56.3
- Grok 4.5xAI55.8
- Claude Sonnet 5Anthropic55.3
- Claude Opus 4.7Anthropic55.0
- Muse Spark 1.1Meta53.2
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| Claude Opus 4.8 | 57.3 |
| Muse Spark 1.2 | 56.8 |
| GPT-5.6 Terra | 56.6 |
| GPT-5.5 | 56.3 |
| Grok 4.5 | 55.8 |
| Claude Sonnet 5 | 55.3 |
| Claude Opus 4.7 | 55.0 |
| Muse Spark 1.1 | 53.2 |
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
- $2
- Output / 1M tokens
- $10
- Cached input / 1M
- $0.2
- Blended 3:1
- $4
One task, estimated
$0.90
- 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
- 1,336
- Win rate
- 55.5%
- Strongest at
- Game development
- Tournaments
- 775
Elo by category
Dot position on a 1,225–1,350 scale · Elo has no meaningful zero
- 1,336
- 1,312
- 1,308
- 1,296
- 1,264
- 1,238
- 1,272
- 1,237
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Game development | 1336 | 55.5% |
| UI components | 1312 | 55.1% |
| 3D scenes | 1308 | 56.1% |
| Websites | 1296 | 55.2% |
| Data visualisation | 1264 | 52.5% |
| SVG | 1238 | 53.7% |
| Full-stack apps | 1272 | 59.8% |
| Mobile apps | 1237 | 55.1% |