Advertise here
#80

Claude Sonnet 5.5

Anthropic Release: 2026-09-29 Tested on: 2026-09-29 21:36 anthropic/claude-sonnet-5.5::high
~1T total (~100B active)MoEClosedEstimated
(max) (xhigh) (high) (medium) (low)

Summary

Claude Sonnet 5.5 scores 8.3 on AI BENCHY and ranks #80. It has 10.0 reliability, a 80.3% pass rate, $0.752 total cost, and 8.94s average response time.

What makes Claude Sonnet 5.5 unique: It stands out most in Puzzle Solving, where it ranks #1, while Data parsing and extraction is its weakest area at #16. It is notably fast compared with similar models.

Model facts

Researched on 2026-09-29

Estimated
Parameters
~1T total (~100B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose parameter counts or architecture. Low-confidence catalog estimates carry forward the prior Claude Sonnet 5 family estimates; the announcement establishes identity and API availability, not these counts. Thinking is always on; OpenRouter lists low, medium, high, xhigh, and max efforts.

Parameter source Availability source

Score

8.3

Consistency

8.3

Reliability

10.0

Total Cost (Current Price)

$0.752

Total Output Tokens

43,305

Total Input Tokens

159,456

Input Price

$2.000 / 1M

Output Price

$10.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 80.3%

Flaky tests

5

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

8.94s

Response Time (max): 25.71s

Response Time (total): 196.68s

Wrong answer: 5 Extra formatting: 1 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#80 Claude Sonnet 5.5

high
Cost
$0.088
Time
73.5s
Tokens
8,914 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Claude Sonnet 5.5highvsClaude Sonnet 5.5xhighClaude Sonnet 5.5highvsGPT-6 LunahighClaude Sonnet 5.5highvsMuse Spark 1.1lowClaude Sonnet 5.5highvsClaude Fable 5.1mediumClaude Sonnet 5.5highvsDeepSeek V4.1 FlashmaxClaude Sonnet 5.5highvsGemini 2.5 FlashmediumClaude Sonnet 5.5highvsGLM 5.3 FlashXmaxClaude Sonnet 5.5highvsMuse Spark 1.3lowClaude Sonnet 5.5highvsInkling SmallhighClaude Sonnet 5.5highvsClaude Sonnet 5medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 8.2 6.9
Data parsing and extraction 7.3 5.8
Domain specific 3.5 4.4
General Intelligence 6.5 3.4
Instructions following 9.9 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models