Navigate
AI BENCHY
Your ad here

AI BENCHY Compare

Anthropic: Claude Sonnet 4.6 vs Google: Gemini 3 Flash Preview

Last updated at: 2026-04-29

Metric Claude Sonnet 4.6 Claude Sonnet 4.6 medium Release: 2026-02-17 Gemini 3 Flash Preview Gemini 3 Flash Preview medium Release: 2025-12-17
Score 8.0 10.0
Rank #36 #1
Reliability N/A N/A
Consistency 9.5 10.0
Tests Correct
Attempt pass rate 74.1% 100.0%
Flaky tests 1 0
Total Runs 54 18
Cost per result 8.930 0.600
Total Cost $1.161 $0.108
Input Price $3.000 / 1M $0.500 / 1M
Output Price $15.000 / 1M $3.000 / 1M
Output Tokens 42,068 655
Reasoning Tokens 26,784 33,749
Response Time (avg) 12.66s 12.11s
Response Time (max) 46.35s 82.37s
Response Time (total) 126.62s 217.93s

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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 6.5 10.0 50.0% 0 2.98s 1,046 1,093
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 3.26s 110 1,076
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 35.76s 6,894 2,097
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 82.37s 144 16,257
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 46.35s 5,871 3,962
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 23.58s 117 3,495
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 13.90s 649 742
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 7.62s 93 2,197
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 2.9 7.2 11.1% 1 0ms 25,790 16,919
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 14.81s 4 7,228
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 4.94s 256 433
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 6.34s 24 635
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 2.61s 318 552
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.30s 24 903
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 4.80s 589 635
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 4.86s 61 1,455
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Output Tokens Reasoning Tokens
Claude Sonnet 4.6 10.0 10.0 100.0% 0 7.48s 655 351
Gemini 3 Flash Preview 10.0 10.0 100.0% 0 9.78s 78 503

Quick Compare

Switch Comparison Pair