Anthropic · Benchmarks

Claude Sonnet 5.5 benchmarks

Claude Sonnet 5.5 has 5 published scores in this dataset, from a Anthropic release dated 2026-09-28. Its composite index is 91.9, which places it 3rd of 22 ranked models. Its strongest area is coding (index 95.2) and its weakest is reasoning (index 88.4). Its best placing is on Terminal-Bench 4.0, where its 70.6 ranks 1st of 16 models with a published score.

Closed APIOfficial page

Category profile

Index 0–100: each score relative to the best published score on that test.

ReasoningCodingAgenticKnowledge
Reasoning
88.41 test · not ranked
Coding
95.2#2 of 13 · 2 tests
Agentic
92.11 test · not ranked
Knowledge
—no data

Model facts

Lab
Anthropic
Type
Closed API
Released
2026-09-28
Context
1M
API price / 1M tokens
$2 in · $10 out

Claude Sonnet 5.5 pricing and open alternatives

Claude Sonnet 5.5 is only available through Anthropic's API, so it cannot be self-hosted; it costs $2 per million input tokens and $10 per million output tokens.

Open-weight alternatives

The highest-ranked open models, which you can run on your own GPU.

Claude Sonnet 5.5 speed and pricing

Measured figures link to their source; estimates are labelled.

API output speed
138 tok/sArtificial Analysis median · Artificial Analysis
Time to first token
1.61 sOpenRouter model page provider stats
API price per 1M tokens
$2.00 in · $10.00 outlab list price · Anthropic pricing docs
Compare speed and price across all models

Score by test

Rank is among every model with a published score on that test.

Humanity's Last Exam56.9%Humanity's Last Exam, no tools; max effort#4 of 23 · 7.5 behind Claude Opus 5.5Humanity's Last Exam (with tools)64.5%Humanity's Last Exam, with tools; max effort#4 of 17 · 5.5 behind Kimi K3.1 ProSWE-bench Pro81.3%SWE-bench Pro; adaptive thinking max effort; avg of 5 trials#2 of 9 · 8.6 behind Claude Opus 5.5Terminal-Bench 4.070.6%Terminal-Bench 4.0; safeguards enabled#1 of 16 · top scoreLMArena Text Elo1477LMArena Text, Overall; snapshot Oct 27, 2026; Claude Sonnet 5.5 (xHigh); +/-7#9 of 21 · 43 behind Gemini 4 Argon

Nearby in the composite ranking

Models with the closest composite index.

  1. 1Claude Opus 5.598.4
  2. 2Kimi K3.1 Pro94.4
  3. 3Claude Sonnet 5.591.9
  4. 4GPT-6 Astra91.4
  5. 5Claude Fable 5.191.2
  6. 6DeepSeek V4 Pro91.0

Head-to-head comparisons

Side-by-side pages built from the tests both models report.

No head-to-head page for Claude Sonnet 5.5 yet. Compare it on the rankings dashboard.

Sources

ModelTestScoreSettingSource
Claude Sonnet 5.5Humanity's Last Exam56.9Humanity's Last Exam, no tools; max effortAnthropic Claude Sonnet 5.5 System Card (Table 8.1.A)
Claude Sonnet 5.5Humanity's Last Exam (with tools)64.5Humanity's Last Exam, with tools; max effortAnthropic Claude Sonnet 5.5 System Card (Table 8.1.A); also in launch post
Claude Sonnet 5.5SWE-bench Pro81.3SWE-bench Pro; adaptive thinking max effort; avg of 5 trialsAnthropic Claude Sonnet 5.5 System Card (Table 8.1.A / sec 8.2)
Claude Sonnet 5.5Terminal-Bench 4.070.6Terminal-Bench 4.0; safeguards enabledAnthropic Claude Sonnet 5.5 System Card (sec 8.5); also in launch post
Claude Sonnet 5.5LMArena Text Elo1477LMArena Text, Overall; snapshot Oct 27, 2026; Claude Sonnet 5.5 (xHigh); +/-7LMArena (arena.ai) Text leaderboard

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works