AI ScoreboardFrontend & Coding Index← Back to rankings

MODEL PROFILE / EDITION 2026.09

Claude Sonnet 5

Teams that need Claude-grade code quality across a whole org at moderate cost

AnthropicRank 23Confidence BNo prior snapshot
74.2

Balanced model evidence score; rank 23. No rank delta is shown because there is no prior numeric snapshot.

Best for

Teams that need Claude-grade code quality across a whole org at moderate cost

Price & access

$2 in / $10 out per 1M; cache read $0.20, cache write $2.50

Evidence summary

Strong first-party and leaderboard coverage for price, context and coding, but no Sonnet-5-specific agentic or debugging benchmark was found.

Edition status

No prior snapshot. Tracked in the September 2026 baseline.

Strengths

  • SWE-bench Verified 85.2% at $2/$10 is the best correctness-per-dollar in the Anthropic line
  • 1M multimodal context and 128K output at mid-tier price
  • Only Claude in this set available on the consumer Free plan
  • Well-sampled Arena row (7,006 votes)

Tradeoffs

  • TTFT 203.67 s at max effort is among the worst measured here
  • Design Arena 1292 and Arena 1543 are mid-pack visually
  • Anthropic docs give no separate Sonnet-5 frontend claims
  • Several AA effort variants have no published score

Score profile

visual 68 · code 80 · agentic 78 · debug 75 · context 92 · speed 52 · value 76

Linked evidence

Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗
Compare this model on the full scoreboard

Use the same published data, filters, and side-by-side metrics.

Open comparison view →