Navigate
AI BENCHY
Advertise here

Claude Opus 5 vs OpenAI: GPT-5.2

Claude Opus 5 (low) leads on average score with 8.6 vs 8.4. GPT-5.2 (medium) has the lower benchmark cost at $0.951 vs $1.121. Claude Opus 5 (low) is faster at 6.99s vs 22.62s, with pass rates of 80.3% vs 72.7%.

Recommended modelClaude Opus 5 (low)It has the best score here (8.6), while responding about 3.2x faster than GPT-5.2 (medium).

Last updated at: 2026-07-25

Metric Claude Opus 5 Claude Opus 5 low Release: 2026-07-25 GPT-5.2 GPT-5.2 medium Release: 2025-12-11
Score 8.6 8.4
Rank #23 #27
Reliability 10.0 10.0
Consistency 9.3 8.5
Tests Correct
Attempt pass rate 80.3% 72.7%
Flaky tests 2 4
Total Runs 66 66
Cost per result 6.593 6.791
Total Cost $1.121 $0.951
Input Price $5.000 / 1M $1.750 / 1M
Output Price $25.000 / 1M $14.000 / 1M
Total Input Tokens 134,773 105,004
Output Tokens 14,123 9,914
Reasoning Tokens 3,896 44,868
Response Time (avg) 6.99s 22.62s
Response Time (max) 30.67s 102.93s
Response Time (total) 153.73s 339.28s

Hamster playing table tennis

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

#23 Claude Opus 5

low
Cost
$0.062
Time
30.2s
Tokens
2,615 tok

#27 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 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 7.8 7.4 77.8% 1 6.70s 10,590 2,442 760
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912

Quick Compare

Switch Comparison Pair