Navigate
AI BENCHY
Advertise here

Claude Opus 5 vs Google: Gemini 3.5 Flash

Claude Opus 5 (medium) leads on average score with 9.2 vs 9.1. Gemini 3.5 Flash (medium) has the lower benchmark cost at $0.642 vs $1.486. Gemini 3.5 Flash (medium) is faster at 8.20s vs 9.38s, with pass rates of 83.3% vs 87.9%.

Recommended modelGemini 3.5 Flash (medium)Its score stays close to the best score here (9.1 vs 9.2), while costing about 2.3x less than Claude Opus 5 (medium).

Last updated at: 2026-07-25

Metric Claude Opus 5 Claude Opus 5 medium Release: 2026-07-25 Gemini 3.5 Flash Gemini 3.5 Flash medium Release: 2026-05-19
Score 9.2 9.1
Rank #12 #14
Reliability 10.0 10.0
Consistency 9.6 9.7
Tests Correct
Attempt pass rate 83.3% 87.9%
Flaky tests 1 1
Total Runs 66 66
Cost per result 8.253 3.374
Total Cost $1.486 $0.642
Input Price $5.000 / 1M $1.500 / 1M
Output Price $25.000 / 1M $9.000 / 1M
Total Input Tokens 135,607 69,747
Output Tokens 25,673 2,166
Reasoning Tokens 6,930 57,436
Response Time (avg) 9.38s 8.20s
Response Time (max) 35.05s 76.68s
Response Time (total) 206.26s 180.47s

Hamster playing table tennis

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

#12 Claude Opus 5

medium
Cost
$0.125
Time
69.3s
Tokens
5,134 tok

#14 Gemini 3.5 Flash

medium
Cost
$0.201
Time
112.9s
Tokens
22,371 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 9.56s 10,590 5,224 1,162
Gemini 3.5 Flash 7.9 7.5 77.8% 1 12.63s 8,118 461 24,939

Quick Compare

Switch Comparison Pair