Claude Sonnet 5.5
Anthropic · Balanced · Sep 28, 2026New
The everyday workhorse of the Claude range: close to Opus on coding and agent benchmarks at half the list price.
- Artificial Analysis Intelligence Index
- 56#2 of 29 · max effort
- API price per 1M tokens
- $2 / $10input / output · $4 blended
- Context window
- 1Mup to 128K output tokens
- Output speed
- 129 t/s7m 41s to first answer at max effort
Benchmark results
Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.
Overall capability
- Artificial Analysis Intelligence Index56#2 of 29
Max effort, default refusal fallback enabled
- Epoch Capabilities Index165#4 of 16
- LiveBench77.8%#9 of 23
Xhigh effort
Coding
- Terminal-Bench 4.061.8%#2 of 13
Claude Code harness, max effort
- Arena WebDev1,773#3 of 27
Xhigh effort
Agents & professional work
- GDPval-AA1,839#2 of 18
Reasoning
- FrontierMath (Tiers 1–3)88.8%#5 of 14
Max effort
- SimpleBench75.9%#8 of 12
Knowledge & science
- GPQA Diamond95.6%#2 of 14
Max effort
Multimodal
- Arena Vision1,268#9 of 15
Xhigh effort
Human preference
- Arena Text1,471#15 of 24
Xhigh effort
Reasoning effort trade-offs
The same model at different thinking budgets. More effort buys a higher intelligence score at a higher cost per task and a longer wait. Measured by Artificial Analysis.
| Effort | Score | Cost / task | First answer | Speed |
|---|---|---|---|---|
| Low | 35.9 | $0.35 | 1.1s | 101 t/s |
| Medium | 40.8 | $0.48 | 2.1s | 102 t/s |
| High | 46.8 | $0.88 | 13s | 104 t/s |
| Xhigh | 51.9 | $2.01 | 36s | 107 t/s |
| Max (headline score) | 56 | $5.46 | 7m 41s | 129 t/s |
Specs & pricing
- Developer
- Anthropic
- Released
- Sep 28, 2026
- Availability
- Generally available
- API model ID
claude-sonnet-5-5- Weights
- Proprietary (API only)
- Reasoning
- Adjustable effort
- Knowledge cutoff
- Jun 2026
- Accepts
- Text, Image
- Produces
- Text
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input price
- $2 / 1M tokens
- Output price
- $10 / 1M tokens
- Cached input
- $0.10 / 1M tokens
Closest alternatives
Models from other labs nearest to Claude Sonnet 5.5 on Artificial Analysis Intelligence Index.
GPT-6 Astra
OpenAI
Intelligence 52.7 · $10 / $50
Compare side by sideGemini 4 Argon
Google
Intelligence 52.6 · $2 / $10
Compare side by sideGPT-6.1 Sol
OpenAI
Intelligence 51.8 · $2 / $10
Compare side by side