AI BENCHY
Advertise here
#30

Claude Sonnet 5

Anthropic Release: 2026-06-30 Tested on: 2026-06-30 21:33 anthropic/claude-sonnet-5::medium
(medium) (none)

Summary

Claude Sonnet 5 scores 7.9 on AI BENCHY and ranks #30. It has 10.0 reliability, a 79.4% pass rate, $0.550 total cost, and 9.94s average response time.

What makes Claude Sonnet 5 unique: It stands out most in Domain specific, where it ranks #1, while Combined is its weakest area at #17.

Score

7.9

Consistency

9.0

Reliability

10.0

Total Cost (Current Price)

$0.550

Total Output Tokens

41,685

Total Input Tokens

67,416

Input Price

$2.000 / 1M

Output Price

$10.000 / 1M

Tests Correct

Wrong Tests: 6

Attempt pass rate: 79.4%

Flaky tests

3

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

Response Time (avg)

9.94s

Response Time (max): 56.94s

Response Time (total): 208.71s

Wrong answer: 4 Did not follow instructions: 1 Invalid tool call: 1

Generation showcase

Hamster playing table tennis

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

#30 Claude Sonnet 5

medium
Cost
$0.007
Time
6.4s
Tokens
832 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-30 21:35 $2.000 / 1M $10.000 / 1M

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 5mediumvsQwen3.5 Plus 2026-02-15mediumClaude Sonnet 5mediumvsGPT-5.4 MinimediumClaude Sonnet 5mediumvsQwen3.6 PlusmediumClaude Sonnet 5mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableClaude Sonnet 5mediumvsClaude Sonnet 4.6mediumClaude Sonnet 5mediumvsGemini 3.5 FlashhighClaude Sonnet 5mediumvsGemini 3 Flash PreviewmediumClaude Sonnet 5mediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 9.0 7.9
Combined 4.5 2.1
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 4.8 3.2
Instructions following 9.9 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models