Navigate
AI BENCHY
Advertise here

Anthropic: Claude Opus 4.7 vs Google: Gemini 3.6 Flash

Gemini 3.6 Flash (low) leads on average score with 9.4 vs 8.7. Gemini 3.6 Flash (low) has the lower benchmark cost at $0.517 vs $1.477. Gemini 3.6 Flash (low) is faster at 4.42s vs 7.61s, with pass rates of 83.3% vs 97.0%.

Recommended modelGemini 3.6 Flash (low)It has the best score here (9.4), while costing about 2.9x less than Claude Opus 4.7 (medium).

Last updated at: 2026-07-21

Metric Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16 Gemini 3.6 Flash Gemini 3.6 Flash low Release: 2026-07-21
Score 8.7 9.4
Rank #18 #6
Reliability 10.0 10.0
Consistency 9.6 9.6
Tests Correct
Attempt pass rate 83.3% 97.0%
Flaky tests 1 1
Total Runs 66 66
Cost per result 8.201 2.461
Total Cost $1.477 $0.517
Input Price $5.000 / 1M $1.500 / 1M
Output Price $25.000 / 1M $7.500 / 1M
Total Input Tokens 145,252 82,715
Output Tokens 24,948 5,729
Reasoning Tokens 5,042 46,633
Response Time (avg) 7.61s 4.42s
Response Time (max) 65.40s 28.92s
Response Time (total) 159.91s 97.13s

Hamster playing table tennis

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

#18 Claude Opus 4.7

medium
Cost
$0.059
Time
26.8s
Tokens
2,475 tok

#6 Gemini 3.6 Flash

low
Cost
$0.050
Time
28.1s
Tokens
6,731 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 7.6 7.2 77.8% 1 12.96s 10,635 7,629 1,114
Gemini 3.6 Flash 7.8 7.4 77.8% 1 7.28s 8,136 451 15,026

Quick Compare

Switch Comparison Pair