Navigate
AI BENCHY
Advertise here

Claude Opus 5 vs Google: Gemini 3.5 Flash

Claude Opus 5 (high) leads on average score with 9.2 vs 8.9. Gemini 3.5 Flash (low) has the lower benchmark cost at $0.433 vs $2.835. Gemini 3.5 Flash (low) is faster at 5.55s vs 20.44s, with pass rates of 84.9% vs 87.9%.

Recommended modelGemini 3.5 Flash (low)Its score stays close to the best score here (8.9 vs 9.2), while costing about 6.6x less than Claude Opus 5 (high).

Last updated at: 2026-07-25

Metric Claude Opus 5 Claude Opus 5 high Release: 2026-07-25 Gemini 3.5 Flash Gemini 3.5 Flash low Release: 2026-05-19
Score 9.2 8.9
Rank #11 #16
Reliability 10.0 10.0
Consistency 9.6 9.7
Tests Correct
Attempt pass rate 84.9% 87.9%
Flaky tests 1 1
Total Runs 66 66
Cost per result 15.747 2.277
Total Cost $2.835 $0.433
Input Price $5.000 / 1M $1.500 / 1M
Output Price $25.000 / 1M $9.000 / 1M
Total Input Tokens 135,959 87,817
Output Tokens 67,066 2,239
Reasoning Tokens 19,114 31,182
Response Time (avg) 20.44s 5.55s
Response Time (max) 159.01s 53.55s
Response Time (total) 449.68s 122.19s

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

#16 Gemini 3.5 Flash

low
Cost
$0.068
Time
39.1s
Tokens
7,588 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
Gemini 3.5 Flash 7.8 10.0 66.7% 0 6.71s 8,118 458 13,420

Quick Compare

Switch Comparison Pair