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

AI BENCHY Compare

Google: Gemini 3 Flash Preview vs StepFun: Step 3.5 Flash

Model Name:

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

Summary

Metric Google: Gemini 3 Flash Preview none Release: Unknown release date StepFun: Step 3.5 Flash medium Release: Unknown release date Free Available
Rank #10 #11
Score 7.21 7.00
Consistency 9.36 8.32
Cost per result 0.078 0.000
Total Cost $0.007 $0.000
Tests Correct
Wrong Tests 4 5
Attempt pass rate 71.8% 73.8%
Flaky tests 1 3
Output Tokens 734 60,502
Reasoning Tokens 0 117,044

Category Breakdown

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 7.00 10.00 66.7% 0 240 0
StepFun: Step 3.5 Flash 10.00 10.00 100.0% 0 13,924 17,208
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 9.88 10.00 100.0% 0 279 0
StepFun: Step 3.5 Flash 10.00 10.00 100.0% 0 535 11,548
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 7.00 10.00 66.7% 0 18 0
StepFun: Step 3.5 Flash 4.00 7.21 44.4% 1 40,942 74,237
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 5.50 5.81 66.7% 1 74 0
StepFun: Step 3.5 Flash 10.00 10.00 100.0% 0 2,121 3,274
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 7.00 10.00 66.7% 0 123 0
StepFun: Step 3.5 Flash 2.00 4.96 33.3% 2 2,705 6,975
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Output Tokens Reasoning Tokens
Google: Gemini 3 Flash Preview 0.00 0.00 0.0% 0 0 0
StepFun: Step 3.5 Flash 10.00 10.00 100.0% 0 275 3,802

Switch Comparison Pair

Compare Google: Gemini 3 Flash Preview against...

Compare StepFun: Step 3.5 Flash against...