Claude Sonnet 5.5 Benchmarks, Pricing & Rankings
Anthropic · 2026-09-22 · Closed · Current
Snapshot 2026-10-14 · updated weekly
Claude Sonnet 5.5 ranks #5 of 42 on the AMR leaderboard.
Claude Sonnet 5.5 benchmark scores
| GPQA Diamond | 92.8% | |
| MMLU-Pro | 89% | |
| SWE-Bench Verified | 76.5% | |
| AIME 2025 | 92.4% | |
| LiveCodeBench v6 | 81.2% | |
| Arena Elo | 1462 |
Claude Sonnet 5.5 price, speed & context
Input price
$3
per 1M tokens
Output price
$15
per 1M tokens
Speed
156
tok/s
Context
500K
tokens
About Claude Sonnet 5.5
Claude Sonnet 5.5 shipped alongside Opus 5.5 and delivers roughly 95% of its sibling’s coding ability at 38% of the output price — the default pick for production coding agents.
Models around Claude Sonnet 5.5 in the rankings
More Anthropic models
Claude Sonnet 5.5 FAQ
Where does Claude Sonnet 5.5 rank?
Claude Sonnet 5.5 ranks #5 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 94.7. Its strongest dimension is GPQA Diamond at 92.8%.
How much does Claude Sonnet 5.5 cost?
Claude Sonnet 5.5 costs $3 per million input tokens and $15 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $12.00 per million tokens.
What is the Claude Sonnet 5.5 context window?
Claude Sonnet 5.5 supports a 500K token context window and generates at a median 156 output tokens per second. That context fits roughly 333 standard documents in a single prompt.
Is Claude Sonnet 5.5 open source?
No — Claude Sonnet 5.5 is a closed model available only through Anthropic’s official API and authorized cloud partners.
What is better than Claude Sonnet 5.5?
Claude Fable 5.1 ranks one place higher at #4 with an AMR score of 94.9. Claude Sonnet 5.5 still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.