AI ScoreboardFrontend & Coding Index← Back to rankings

MODEL PROFILE / EDITION 2026.09

Claude Opus 4.7

Long-lived integrations that need a stable, heavily validated Claude with good visual taste

AnthropicRank 22Confidence ANo prior snapshot
74.3

Balanced model evidence score; rank 22. No rank delta is shown because there is no prior numeric snapshot.

Best for

Long-lived integrations that need a stable, heavily validated Claude with good visual taste

Price & access

$5 in / $25 out per 1M; cache read $0.50, cache write $6.25

Evidence summary

Bedrock card, Anthropic pricing, the largest Arena sample in the Anthropic family, Design Arena and two third-party leaderboards.

Edition status

No prior snapshot. Tracked in the September 2026 baseline.

Strengths

  • Best-sampled Anthropic Arena row in this set (14,142 votes, +/-6)
  • Design Arena Website 1310 beats Opus 4.8 and Sonnet 5
  • SWE-bench Verified 87.6% with a documented Adaptive mode
  • Lowest TTFT of the Opus tier (24.39 s)

Tradeoffs

  • Two generations behind Opus 5 at identical $5/$25 pricing
  • Legacy on Anthropic's pricing page
  • SWE-bench Pro 64.3% trails Opus 4.8's 69.2%
  • Effort aliases are indistinguishable on Arena, complicating comparisons

Score profile

visual 71 · code 82 · agentic 79 · debug 76 · context 92 · speed 60 · value 55

Linked evidence

Evidence source 1 ↗Evidence source 2 ↗Evidence source 3 ↗Evidence source 4 ↗Evidence source 5 ↗Evidence source 6 ↗Evidence source 7 ↗
Compare this model on the full scoreboard

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

Open comparison view →