The honest view from inside technical leadership
LLM Leaderboard · Anthropic

Claude Sonnet 5.5

Benchmarks, pricing and rank for Claude Sonnet 5.5, with every score linked to the leaderboard that published it.

← All models

#787.1CTO Index
Provider
Anthropic
Weights
Closed
License
Proprietary
Price $/M in / out
$2 / $10
Context window
1M
Benchmarks covered
5 of 5

Benchmark results

Terminal-Bench 4.1Agentic coding
63.9%
#5 of 41 tracked · source
WebDev ArenaCoding (human-judged)
1772
#3 of 44 tracked · source
ARC-AGI-2Reasoning
83.9%
#17 of 28 tracked · source
Text ArenaGeneral chat (human-judged)
1473
#26 of 40 tracked · source
ARC-AGI-3Interactive reasoning
24.3%
#9 of 19 tracked · source

Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works

Compare Claude Sonnet 5.5

Frequently asked questions

How good is Claude Sonnet 5.5?

Claude Sonnet 5.5 ranks #7 of 39 models on the Diary of a CTO Index with 87.1 points.

How much does Claude Sonnet 5.5 cost?

Claude Sonnet 5.5 lists at $2 / $10 per million input / output tokens.

What are Claude Sonnet 5.5's benchmark scores?

Terminal-Bench 4.1: 63.9%; WebDev Arena: 1772; ARC-AGI-2: 83.9%; Text Arena: 1473; ARC-AGI-3: 24.3%.

What is Claude Sonnet 5.5's context window?

Claude Sonnet 5.5 supports a context window of 1M tokens.