Navigate
AI BENCHY
Advertise here

Compared models

Gemma 4 31B (medium) vs Gemini 3 PRO Preview (medium) vs GLM 5 Turbo (medium) benchmark comparison: GLM 5 Turbo (medium) leads on Score with 7.6. 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
#185
Total Output Tokens
11,592
Response Time (avg)
9.05s
Total Cost
$0.385
Rank
#77
Total Output Tokens
74,522
Response Time (avg)
23.00s
Total Cost
$0.323
Recommended model GLM 5 Turbo (medium)

It has the best score here (7.6), while responding about 1.9x 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 PRO Preview Gemini 3 PRO Preview medium Release: 2025-11-18 GLM 5 Turbo GLM 5 Turbo medium Release: 2026-03-15
Score 6.2 6.0 7.6
Rank #166 #185 #77
Reliability 10.0 N/A 10.0
Consistency 8.7 9.5 8.1
Attempts 66/66 63/66 63/66
Tests Correct
Attempt pass rate 65.2% 63.6% 71.2%
Flaky tests 3 0 4
Total Runs 66 63 63
Cost per result 1.152 1.406 2.011
Total Cost $0.100 $0.385 $0.323
Input Price $0.090 / 1M $9.506 / 1M $1.200 / 1M
Output Price $0.340 / 1M $9.506 / 1M $4.000 / 1M
Total Input Tokens 94,969 28,848 35,593
Output Tokens 34,399 1,490 12,245
Reasoning Tokens 233,022 10,102 62,277
Response Time (avg) 78.59s 9.05s 23.00s
Response Time (max) 437.40s 26.24s 194.23s
Response Time (total) 1571.84s 90.53s 482.97s
Parameters 30.7B ~1.2T total (~20B active) 744B total (40B active)
Availability Open source 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

#185 Gemini 3 PRO Preview

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

#77 GLM 5 Turbo

medium
Cost
$0.074
Time
206.0s
Tokens
18,549 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 PRO Preview 3.0 10.0 0.0% 0 0ms 0 0 0
GLM 5 Turbo 8.2 9.3 66.7% 0 45.90s 5,941 363 25,381

Quick Compare

Switch Comparison Pair