Navigate
Advertise here

Claude Sonnet 4.6 (medium) vs Claude Sonnet 5 (medium)

Claude Sonnet 5 (medium) leads on average score with 8.5 vs 6.4. Claude Sonnet 5 (medium) has the lower benchmark cost at $1.438 vs $2.126. Claude Sonnet 5 (medium) is faster at 15.01s vs 28.08s, with pass rates of 62.3% vs 76.8%.

Last updated at: 2026-11-17

Compared models

Rank
#298
Total Output Tokens
120,427
Response Time (avg)
28.08s
Total Cost
$2.126
Rank
#121
Total Output Tokens
73,018
Response Time (avg)
15.01s
Total Cost
$1.438
Recommended model Claude Sonnet 5 (medium)

It has the best score here (8.5), while responding about 1.9x faster than Claude Sonnet 4.6 (medium).

Detailed comparison

Metric Claude Sonnet 4.6 Claude Sonnet 4.6 medium Release: 2026-02-17 Claude Sonnet 5 Claude Sonnet 5 medium Release: 2026-06-30
Score 6.4 8.5
Rank #298 #121
Reliability 10.0 10.0
Consistency 9.1 9.1
Attempts 66/69 69/69
Tests Correct
Attempt pass rate 62.3% 76.8%
Flaky tests 1 3
Total Runs 66 69
Cost per result 15.182 8.985
Total Cost $2.126 $1.438
Input Price $3.000 / 1M $2.000 / 1M
Output Price $15.000 / 1M $10.000 / 1M
Cache Read Price $0.300 / 1M $0.200 / 1M
Cache Write Price $3.750 / 1M $2.500 / 1M
Total Input Tokens 106,316 353,658
Output Tokens 79,338 54,891
Reasoning Tokens 41,089 18,370
Response Time (avg) 28.08s 15.01s
Response Time (max) 140.96s 69.26s
Response Time (total) 421.15s 345.16s
Parameters ~1T total (~100B active) ~1T total (~100B active)
Availability Closed Closed

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#298 Claude Sonnet 4.6

medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
Cost
$0.000
Time
300.0s
Tokens
0 tok

#121 Claude Sonnet 5

medium
Cost
$0.007
Time
6.4s
Tokens
832 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 Sonnet 4.6 5.7 6.6 44.4% 1 33.29s 6,995 16,089 3,686
Claude Sonnet 5 9.0 7.9 88.9% 1 17.28s 10,590 13,153 2,379

Switch Comparison Pair