AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#81

Claude Opus 5

Anthropic Release: 2026-07-25 Tested on: 2026-08-14 02:24 anthropic/claude-opus-5::none
~5T total (~500B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

Claude Opus 5 scores 7.5 on AI BENCHY and ranks #81. It has 10.0 reliability, a 57.6% pass rate, $1.550 total cost, and 7.65s average response time.

What makes Claude Opus 5 unique: It stands out most in General Intelligence, where it ranks #1, while Anti-AI Tricks is its weakest area at #16.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~5T total (~500B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. External industry estimate; vendor has not disclosed the architecture.

Parameter source Availability source

Score

7.5

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$1.550

Total Output Tokens

24,866

Total Input Tokens

185,547

Input Price

$5.000 / 1M

Output Price

$25.000 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 57.6%

Flaky tests

1

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

Response Time (avg)

7.65s

Response Time (max): 47.72s

Response Time (total): 168.35s

Wrong answer: 6 Extra formatting: 2 Invalid tool call: 1 No answer: 1

Hamster playing table tennis

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

#81 Claude Opus 5

none
Cost
$0.271
Time
149.3s
Tokens
10,962 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:24 Re-test 7.5 10.0 $1.550 Current run
2026-07-25 03:41 Initial run 7.5 10.0 $1.550 Compare

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

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-14 12:51 $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 5nonevsNemotron 3 UltramediumFree AvailableClaude Opus 5nonevsGPT-5.4 NanomediumClaude Opus 5nonevsSolar Pro 4xhighClaude Opus 5nonevsGPT-5.6 TerralowClaude Opus 5nonevsGPT-5.6 LunahighClaude Opus 5nonevsMiniMax M3mediumClaude Opus 5nonevsDeepSeek V4 Flash 0423highClaude Opus 5nonevsGPT 5.3 ChatnoneClaude Opus 5nonevsDeepSeek V4 ProhighClaude Opus 5nonevsQwen3.5 Plus 2026-02-15medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 5.5 8.3
Coding 5.9 9.7
Combined 8.3 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models