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

AI BENCHY Compare

Google: Gemini 3 Flash Preview vs MoonshotAI: Kimi K2.5

Model Name:

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

Summary

Metric Google: Gemini 3 Flash Preview medium Release: Unknown release date MoonshotAI: Kimi K2.5 medium Release: Unknown release date
Rank #1 #17
Score 9.93 6.29
Consistency 10.00 7.69
Cost per result 0.815 2.335
Total Cost $0.114 $0.187
Tests Correct
Wrong Tests 0 6
Attempt pass rate 100.0% 73.8%
Flaky tests 0 4
Output Tokens 1,111 30,504
Reasoning Tokens 34,409 58,467

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 10.00 10.00 100.0% 0 299 3,127
MoonshotAI: Kimi K2.5 7.00 7.21 88.9% 1 335 6,255
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 10.00 10.00 100.0% 0 292 5,467
MoonshotAI: Kimi K2.5 10.00 10.00 100.0% 0 1,181 6,049
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 10.00 10.00 100.0% 0 12 15,295
MoonshotAI: Kimi K2.5 1.00 4.41 33.3% 2 20,696 30,894
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 10.00 10.00 100.0% 0 72 4,092
MoonshotAI: Kimi K2.5 9.50 10.00 100.0% 0 3,777 4,967
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 9.67 10.00 100.0% 0 202 5,298
MoonshotAI: Kimi K2.5 5.00 7.61 55.6% 1 4,273 9,490
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 10.00 10.00 100.0% 0 234 1,130
MoonshotAI: Kimi K2.5 10.00 10.00 100.0% 0 242 812

Switch Comparison Pair