AI BENCHY
Advertise here
#47

Claude Sonnet 4.6

Anthropic Release: 2026-02-17 Tested on: 2026-05-22 00:14 anthropic/claude-sonnet-4.6::medium
(medium) (none)

Summary

Claude Sonnet 4.6 scores 7.6 on AI BENCHY and ranks #47. It has 10.0 reliability, a 68.3% pass rate, $1.330 total cost, and 15.72s average response time.

What makes Claude Sonnet 4.6 unique: It stands out most in General Intelligence, where it ranks #1, while Domain specific is its weakest area at #15.

Score

7.6

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$1.330

Total Output Tokens

79,442

Total Input Tokens

0

Input Price

$3.000 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 68.3%

Flaky tests

2

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

Response Time (avg)

15.72s

Response Time (max): 46.35s

Response Time (total): 188.69s

Extra formatting: 3 Wrong answer: 3 Timed out: 1

Generation showcase

Hamster playing table tennis

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

#47 Claude Sonnet 4.6

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:42 New test added 7.4 10.0 $1.418 Compare
2026-05-22 00:14 Suite changed 7.6 10.0 $1.330 Current run
2026-04-11 01:44 First recorded run 8.0 N/A $1.161 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

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 4.6mediumvsClaude Sonnet 5mediumClaude Sonnet 4.6mediumvsQwen3.5-27BmediumClaude Sonnet 4.6mediumvsGemini 3.1 Flash Lite PreviewmediumClaude Sonnet 4.6mediumvsQwen3.5 Plus 2026-02-15mediumClaude Sonnet 4.6mediumvsQwen3.5 Plus 2026-04-20mediumClaude Sonnet 4.6mediumvsGemini 3.5 FlashhighClaude Sonnet 4.6mediumvsGemini 3 Flash PreviewmediumClaude Sonnet 4.6mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableClaude Sonnet 4.6mediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.5 10.0
Coding 6.9 6.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 2.9 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models