AI BENCHY
Advertise here
#2

Gemini 3.1 Pro Preview

Google Release: 2026-02-19 Tested on: 2026-04-11 01:44 google/gemini-3.1-pro-preview::medium

Summary

Gemini 3.1 Pro Preview scores 9.6 on AI BENCHY and ranks #2. It has N/A reliability, a 94.4% pass rate, $0.578 total cost, and 15.96s average response time.

What makes Gemini 3.1 Pro Preview unique: It is one of the highest-ranked models overall. Its total benchmark cost is unusually low for its score range.

Score

9.6

Consistency

10.0

Reliability

N/A

Total Cost (Current Price)

$0.578

Total Output Tokens

42,474

Total Input Tokens

0

Input Price

$2.000 / 1M

Output Price

$12.000 / 1M

Tests Correct

Wrong Tests: 1

Attempt pass rate: 94.4%

Flaky tests

0

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

15.96s

Response Time (max): 40.61s

Response Time (total): 175.52s

Wrong answer: 1

Generation showcase

Hamster playing table tennis

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

#2 Gemini 3.1 Pro Preview

medium
Cost
$0.115
Time
87.2s
Tokens
9,629 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 14:04 New test added 9.4 10.0 $1.054 Compare
2026-05-22 00:30 Suite changed 9.3 10.0 $1.006 Compare
2026-04-11 01:44 First recorded run 9.6 N/A $0.578 Current run

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Gemini 3.1 Pro PreviewmediumvsClaude Fable 5mediumGemini 3.1 Pro PreviewmediumvsGemini 3.5 FlashmediumGemini 3.1 Pro PreviewmediumvsGemini 3.5 FlashlowGemini 3.1 Pro PreviewmediumvsGPT-5.5mediumGemini 3.1 Pro PreviewmediumvsGPT-5.5lowGemini 3.1 Pro PreviewmediumvsGPT-5.3-CodexmediumGemini 3.1 Pro PreviewmediumvsGemini 3.5 FlashhighGemini 3.1 Pro PreviewmediumvsGemini 3 Flash PreviewmediumGemini 3.1 Pro PreviewmediumvsNemotron 3 Ultra 550b A55bmediumFree Available

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 9.5 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0

Compared models