Navigate
AI BENCHY
Advertise here

Anthropic: Claude Sonnet 5 vs OpenAI: GPT-5.4

GPT-5.4 (medium) leads on average score with 8.5 vs 8.3. Claude Sonnet 5 (medium) has the lower benchmark cost at $0.922 vs $1.533. Claude Sonnet 5 (medium) is faster at 12.52s vs 23.10s, with pass rates of 80.3% vs 77.3%.

Recommended modelClaude Sonnet 5 (medium)Its score stays close to the best score here (8.3 vs 8.5), while costing about 1.7x less than GPT-5.4 (medium).

Last updated at: 2026-07-22

Metric Claude Sonnet 5 Claude Sonnet 5 medium Release: 2026-06-30 GPT-5.4 GPT-5.4 medium Release: 2026-03-05
Score 8.3 8.5
Rank #26 #21
Reliability 10.0 10.0
Consistency 9.0 8.6
Tests Correct
Attempt pass rate 80.3% 77.3%
Flaky tests 3 4
Total Runs 66 66
Cost per result 5.760 10.220
Total Cost $0.922 $1.533
Input Price $2.000 / 1M $2.500 / 1M
Output Price $10.000 / 1M $15.000 / 1M
Total Input Tokens 145,956 81,127
Output Tokens 52,333 6,155
Reasoning Tokens 10,874 82,515
Response Time (avg) 12.52s 23.10s
Response Time (max) 66.71s 100.41s
Response Time (total) 275.42s 508.26s

Hamster playing table tennis

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

#26 Claude Sonnet 5

medium
Cost
$0.007
Time
6.4s
Tokens
832 tok

#21 GPT-5.4

medium
Cost
$0.214
Time
199.6s
Tokens
14,349 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 5 9.0 7.9 88.9% 1 17.28s 10,590 13,153 2,379
GPT-5.4 8.8 7.8 88.9% 1 44.36s 7,305 433 24,216

Quick Compare

Switch Comparison Pair