AI BENCHY
Advertise here
#70

Claude Opus 4.8

Anthropic Release: 2026-05-28 Tested on: 2026-06-30 22:01 anthropic/claude-opus-4.8::none
(medium) (low) (none)

Summary

Claude Opus 4.8 scores 7.2 on AI BENCHY and ranks #70. It has 10.0 reliability, a 61.9% pass rate, $0.539 total cost, and 3.48s average response time.

What makes Claude Opus 4.8 unique: It stands out most in Instructions following, where it ranks #3, while Data parsing and extraction is its weakest area at #12. It is notably fast compared with similar models.

Score

7.2

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$0.539

Total Output Tokens

8,107

Total Input Tokens

67,104

Input Price

$5.000 / 1M

Output Price

$25.000 / 1M

Tests Correct

Wrong Tests: 9

Attempt pass rate: 61.9%

Flaky tests

2

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

Response Time (avg)

3.48s

Response Time (max): 17.73s

Response Time (total): 73.00s

Wrong answer: 4 Extra formatting: 3 Did not follow instructions: 1 No answer: 1

Generation showcase

Hamster playing table tennis

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

#70 Claude Opus 4.8

none
Cost
$0.053
Time
22.0s
Tokens
2,253 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-30 22:01 Re-test 7.2 10.0 $0.539 Current run
2026-06-04 13:44 New test added 7.0 10.0 $0.539 Compare
2026-05-28 17:34 Initial run 7.3 10.0 $0.519 Compare

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $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 4.8nonevsGemini 3 Flash PreviewlowClaude Opus 4.8nonevsMiMo-V2.5-PromediumClaude Opus 4.8nonevsClaude Sonnet 4.6noneClaude Opus 4.8nonevsSeed-2.0-MinimediumClaude Opus 4.8nonevsGemini 3.5 FlashhighClaude Opus 4.8nonevsGemini 3 Flash PreviewmediumClaude Opus 4.8nonevsNemotron 3 Ultra 550b A55bmediumFree AvailableClaude Opus 4.8nonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.5 10.0
Coding 5.5 10.0
Combined 9.5 10.0
Data parsing and extraction 7.3 5.8
Domain specific 5.3 7.2
General Intelligence 10.0 10.0
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