AI BENCHY
Advertise here
#23

Claude Opus 5

Anthropic Release: 2026-07-25 Tested on: 2026-07-25 03:41 anthropic/claude-opus-5::low
(high) (medium) (low) (none)

Summary

Claude Opus 5 scores 8.6 on AI BENCHY and ranks #23. It has 10.0 reliability, a 80.3% pass rate, $1.121 total cost, and 6.99s average response time.

What makes Claude Opus 5 unique: It is notably fast compared with similar models.

Score

8.6

Consistency

9.3

Reliability

10.0

Total Cost (Current Price)

$1.121

Total Output Tokens

18,019

Total Input Tokens

134,773

Input Price

$5.000 / 1M

Output Price

$25.000 / 1M

Tests Correct

Wrong Tests: 5

Attempt pass rate: 80.3%

Flaky tests

2

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

Response Time (avg)

6.99s

Response Time (max): 30.67s

Response Time (total): 153.73s

Wrong answer: 5

Hamster playing table tennis

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

#23 Claude Opus 5

low
Cost
$0.062
Time
30.2s
Tokens
2,615 tok

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-25 04:00 $5.000 / 1M $25.000 / 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 Opus 5lowvsClaude Fable 5mediumClaude Opus 5lowvsGPT-5.4mediumClaude Opus 5lowvsMuse Spark 1.1mediumClaude Opus 5lowvsQwen3.6 Max PreviewmediumClaude Opus 5lowvsClaude Opus 4.7mediumClaude Opus 5lowvsGrok 4.5lowClaude Opus 5lowvsClaude Opus 4.8mediumClaude Opus 5lowvsGPT-5.2mediumClaude Opus 5lowvsGPT-5.3-CodexmediumClaude Opus 5lowvsGrok 4.5medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 7.8 7.4
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