Navigate
AI BENCHY
Advertise here

Anthropic: Claude Opus 4.7 vs Anthropic: Claude Sonnet 4.6

Claude Opus 4.7 (medium) leads on average score with 8.7 vs 7.8. Claude Opus 4.7 (medium) has the lower benchmark cost at $1.477 vs $2.057. Claude Opus 4.7 (medium) is faster at 7.61s vs 25.91s, with pass rates of 83.3% vs 66.7%.

Recommended modelClaude Opus 4.7 (medium)It has the best score here (8.7), while responding about 3.4x faster than Claude Sonnet 4.6 (medium).

Last updated at: 2026-07-20

Metric Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16 Claude Sonnet 4.6 Claude Sonnet 4.6 medium Release: 2026-02-17
Score 8.7 7.8
Rank #15 #40
Reliability 10.0 10.0
Consistency 9.6 9.2
Tests Correct
Attempt pass rate 83.3% 66.7%
Flaky tests 1 2
Total Runs 66 66
Cost per result 8.201 14.692
Total Cost $1.477 $2.057
Input Price $5.000 / 1M $3.000 / 1M
Output Price $25.000 / 1M $15.000 / 1M
Total Input Tokens 145,252 106,292
Output Tokens 24,948 80,748
Reasoning Tokens 5,042 35,117
Response Time (avg) 7.61s 25.91s
Response Time (max) 65.40s 140.96s
Response Time (total) 159.91s 362.78s

Hamster playing table tennis

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

#15 Claude Opus 4.7

medium
Cost
$0.059
Time
26.8s
Tokens
2,475 tok

#40 Claude Sonnet 4.6

medium
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 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 4.7 7.6 7.2 77.8% 1 12.96s 10,635 7,629 1,114
Claude Sonnet 4.6 5.7 6.6 44.4% 1 33.29s 6,995 16,089 3,686

Quick Compare

Switch Comparison Pair