Navigate
AI BENCHY
Compare Charts
❤️ Made by XCS
Your ad here

AI BENCHY Compare

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

Model Name:

Last updated at : 2026-02-27 15:16

Summary

Metric Anthropic: Claude Sonnet 4.6 medium Release: Unknown release date Google: Gemini 3 Pro Preview medium Release: Unknown release date
Rank #8 #3
Score 7.43 8.64
Consistency 9.40 10.00
Cost per result 8.105 0.947
Total Cost $0.811 $0.114
Tests Correct
Wrong Tests 4 2
Attempt pass rate 73.8% 85.7%
Flaky tests 1 0
Output Tokens 29,098 1,100
Reasoning Tokens 20,435 5,910

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 7.00 10.00 66.7% 0 1,031 1,093
Google: Gemini 3 Pro Preview 10.00 10.00 100.0% 0 143 1,107
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 10.00 10.00 100.0% 0 727 907
Google: Gemini 3 Pro Preview 10.00 10.00 100.0% 0 318 687
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 1.00 7.21 11.1% 1 25,790 16,919
Google: Gemini 3 Pro Preview 4.00 10.00 33.3% 0 15 1,211
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 10.00 10.00 100.0% 0 316 523
Google: Gemini 3 Pro Preview 9.50 10.00 100.0% 0 69 754
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 10.00 10.00 100.0% 0 579 642
Google: Gemini 3 Pro Preview 10.00 10.00 100.0% 0 231 1,180
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Anthropic: Claude Sonnet 4.6 10.00 10.00 100.0% 0 655 351
Google: Gemini 3 Pro Preview 10.00 10.00 100.0% 0 324 971

Switch Comparison Pair