MODEL PROFILE / EDITION 2026.09
Claude Sonnet 4.6
Latency-sensitive interactive UI work where instant first tokens matter more than peak reasoning
Balanced model evidence score; rank 27. No rank delta is shown because there is no prior numeric snapshot.
Best for
Latency-sensitive interactive UI work where instant first tokens matter more than peak reasoning
Price & access
$3 in / $15 out per 1M - more expensive than the newer Sonnet 5 at $2/$10; cache read $0.30, cache write $3.75
Evidence summary
Largest Arena sample in the set, a standardised-scaffold SWE-Rebench result, Bedrock card and Anthropic pricing all available.
Edition status
No prior snapshot. Tracked in the September 2026 baseline.
Strengths
- The most heavily voted Arena row here (19,843 votes, +/-5) - the tightest confidence interval in the set
- SWE-Rebench 60.7% under a standardised ReAct scaffold, one of very few contamination-resistant results available
- TTFT 1.51 s in non-reasoning mode - near-instant responses
- Design Arena 1300 beats several newer models
Tradeoffs
- Costs more than the newer, better Sonnet 5
- 64K max output is half the current Claude standard
- AA Intelligence Index 29 in non-reasoning mode is low
- Legacy status on Anthropic's pricing page
Score profile
visual 66 · code 72 · agentic 70 · debug 69 · context 88 · speed 70 · value 66
Linked evidence
Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Evidence source 7 ↗Use the same published data, filters, and side-by-side metrics.