Navigate
AI BENCHY
Advertise here

Anthropic: Claude Opus 4.7 vs Google: Gemini 3.5 Flash

Gemini 3.5 Flash (high) leads on average score with 9.5 vs 6.6. Claude Opus 4.7 has the lower benchmark cost at $0.505 vs $1.976. Claude Opus 4.7 is faster at 3.02s vs 15.07s, with pass rates of 72.7% vs 93.9%.

Recommended modelGemini 3.5 Flash (high)It has the strongest score in this comparison (9.5) and the best overall balance of cost and response time across all 2 models.

Last updated at: 2026-07-17

Metric Claude Opus 4.7 Claude Opus 4.7 none Release: 2026-04-16 Gemini 3.5 Flash Gemini 3.5 Flash high Release: 2026-05-19
Score 6.6 9.5
Rank #90 #2
Reliability 10.0 10.0
Consistency 8.6 9.3
Tests Correct
Attempt pass rate 72.7% 93.9%
Flaky tests 0 2
Total Runs 57 66
Cost per result 3.154 9.879
Total Cost $0.505 $1.976
Input Price $5.000 / 1M $1.500 / 1M
Output Price $25.000 / 1M $9.000 / 1M
Total Input Tokens 69,576 107,137
Output Tokens 6,265 8,777
Reasoning Tokens 0 192,900
Response Time (avg) 3.02s 15.07s
Response Time (max) 18.27s 145.92s
Response Time (total) 57.44s 331.48s

Hamster playing table tennis

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

#90 Claude Opus 4.7

none
Cost
$0.051
Time
24.2s
Tokens
2,181 tok

#2 Gemini 3.5 Flash

high
Cost
$0.208
Time
118.2s
Tokens
23,158 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 4.7 3.3 3.3 33.3% 0 2.84s 1,176 494 0
Gemini 3.5 Flash 10.0 10.0 100.0% 0 22.96s 8,118 456 47,129

Quick Compare

Switch Comparison Pair