Navigate
AI BENCHY
Advertise here

Compared models

Gemma 4 31B (medium) vs Gemini 3 Flash Preview (medium) vs Gemini 3 PRO Preview (medium) vs Gemini 3.1 Pro Preview (medium) benchmark comparison: Gemini 3 Flash Preview (medium) leads on Score with 9.5. Gemma 4 31B (medium) leads on Reliability with 10.0. Gemma 4 31B (medium) has the lowest Total Cost at $0.100. Gemini 3 PRO Preview (medium) is fastest at 9.05s.

Last updated at: 2026-08-20

Rank
#166
Total Output Tokens
267,421
Response Time (avg)
78.59s
Total Cost
$0.100
Rank
#5
Total Output Tokens
239,608
Response Time (avg)
19.86s
Total Cost
$0.763
Rank
#185
Total Output Tokens
11,592
Response Time (avg)
9.05s
Total Cost
$0.385
Rank
#12
Total Output Tokens
97,238
Response Time (avg)
20.62s
Total Cost
$1.352
Recommended model Gemini 3 Flash Preview (medium)

It has the best score here (9.5), while responding about 1.8x faster than the other models in this comparison.

Detailed comparison

Metric Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available Gemini 3 Flash Preview Gemini 3 Flash Preview medium Release: 2025-12-17 Gemini 3 PRO Preview Gemini 3 PRO Preview medium Release: 2025-11-18 Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium Release: 2026-02-19
Score 6.2 9.5 6.0 9.2
Rank #166 #5 #185 #12
Reliability 10.0 10.0 N/A 10.0
Consistency 8.7 9.7 9.5 10.0
Attempts 66/66 66/66 63/66 66/66
Tests Correct
Attempt pass rate 65.2% 93.9% 63.6% 90.9%
Flaky tests 3 1 0 0
Total Runs 66 66 63 66
Cost per result 1.152 3.814 1.406 6.758
Total Cost $0.100 $0.763 $0.385 $1.352
Input Price $0.090 / 1M $0.500 / 1M $9.506 / 1M $2.000 / 1M
Output Price $0.340 / 1M $3.000 / 1M $9.506 / 1M $12.000 / 1M
Total Input Tokens 94,969 87,870 28,848 92,296
Output Tokens 34,399 5,486 1,490 5,232
Reasoning Tokens 233,022 234,122 10,102 92,006
Response Time (avg) 78.59s 19.86s 9.05s 20.62s
Response Time (max) 437.40s 117.26s 26.24s 88.68s
Response Time (total) 1571.84s 436.88s 90.53s 329.94s
Parameters 30.7B ~500B total (~20B active) ~1.2T total (~20B active) ~1.2T total (~20B active)
Availability Open source Closed Closed Closed

Model generation showcase

Hamster playing table tennis

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

#166 Gemma 4 31B

medium
Cost
$0.002
Time
45.7s
Tokens
2,696 tok

#5 Gemini 3 Flash Preview

medium
Cost
$0.010
Time
18.4s
Tokens
3,351 tok

#185 Gemini 3 PRO Preview

medium
No endpoints found for google/gemini-3-pro-preview.
Cost
$0.000
Time
0.1s
Tokens
0 tok

#12 Gemini 3.1 Pro Preview

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

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

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Gemma 4 31B 4.3 5.8 22.2% 1 219.76s 5,568 11,098 33,212
Gemini 3 Flash Preview 8.6 7.6 88.9% 1 84.40s 8,122 462 161,084
Gemini 3 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0
Gemini 3.1 Pro Preview 7.9 9.9 66.7% 0 40.17s 8,124 435 41,247

Quick Compare

Switch Comparison Pair