Advertise here
#20

Claude Opus 5.5

Anthropic Release: 2026-09-23 Tested on: 2026-09-23 05:09 anthropic/claude-opus-5.5::low
~5T total (~500B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

Claude Opus 5.5 scores 9.3 on AI BENCHY and ranks #20. It has 10.0 reliability, a 87.9% pass rate, $0.952 total cost, and 23.72s average response time.

Model facts

Researched on 2026-09-23

Estimated
Parameters
~5T total (~500B 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 estimate carries forward the prior anthropic/claude-opus-5 family estimate; the linked announcement establishes identity and availability, not these counts.

Parameter source Availability source

Score

9.3

Consistency

9.3

Reliability

10.0

Total Cost (Current Price)

$0.952

Total Output Tokens

21,004

Total Input Tokens

132,746

Input Price

$4.000 / 1M

Output Price

$20.000 / 1M

Tests Correct

Wrong Tests: 4

Attempt pass rate: 87.9%

Flaky tests

2

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

Response Time (avg)

23.72s

Response Time (max): 89.16s

Response Time (total): 521.82s

Wrong answer: 2 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

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

#20 Claude Opus 5.5

low
Invalid SVG
Cost
$0.038
Time
19.1s
Tokens
2,010 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 Opus 5.5lowvsGrok 4.6highClaude Opus 5.5lowvsClaude Opus 5.5highClaude Opus 5.5lowvsGPT-5.5lowClaude Opus 5.5lowvsGemini 3.1 Pro PreviewmediumClaude Opus 5.5lowvsGPT-5.6 SolhighClaude Opus 5.5lowvsGemini 3.7 FlashlowClaude Opus 5.5lowvsGPT-6 AstramediumClaude Opus 5.5lowvsClaude Opus 5highClaude Opus 5.5lowvsGPT-5.6 SolmediumClaude Opus 5.5lowvsClaude Opus 5medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.9 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 8.7 7.7
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models