Navigate
AI BENCHY
Advertise here

Claude Opus 5 vs Claude Opus 5

The average score is effectively tied at 9.2 vs 9.2. Claude Opus 5 (medium) has the lower benchmark cost at $1.486 vs $2.835. Claude Opus 5 (medium) is faster at 9.38s vs 20.44s, with pass rates of 84.9% vs 83.3%.

Recommended modelClaude Opus 5 (medium)It has the best score here (9.2), while costing about 1.9x less than Claude Opus 5 (high).

Last updated at: 2026-07-25

Metric Claude Opus 5 Claude Opus 5 high Release: 2026-07-25 Claude Opus 5 Claude Opus 5 medium Release: 2026-07-25
Score 9.2 9.2
Rank #11 #12
Reliability 10.0 10.0
Consistency 9.6 9.6
Tests Correct
Attempt pass rate 84.9% 83.3%
Flaky tests 1 1
Total Runs 66 66
Cost per result 15.747 8.253
Total Cost $2.835 $1.486
Input Price $5.000 / 1M $5.000 / 1M
Output Price $25.000 / 1M $25.000 / 1M
Total Input Tokens 135,959 135,607
Output Tokens 67,066 25,673
Reasoning Tokens 19,114 6,930
Response Time (avg) 20.44s 9.38s
Response Time (max) 159.01s 35.05s
Response Time (total) 449.68s 206.26s

Hamster playing table tennis

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

#11 Claude Opus 5

high
Cost
$0.265
Time
144.5s
Tokens
10,741 tok

#12 Claude Opus 5

medium
Cost
$0.125
Time
69.3s
Tokens
5,134 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Claude Opus 5 10.0 10.0 100.0% 0 12.73s 10,590 7,547 1,721
Claude Opus 5 10.0 10.0 100.0% 0 9.56s 10,590 5,224 1,162

Quick Compare

Switch Comparison Pair