Navigate
AI BENCHY
Advertise here

Gemini 3.7 Flash — high vs medium

high leads on average score with 9.8 vs 9.4. medium has the lower benchmark cost at $0.309 vs $0.646. medium is faster at 5.87s vs 12.22s, with pass rates of 95.5% vs 93.9%.

Last updated at: 2026-09-04

Rank
#6
Total Output Tokens
154,846
Response Time (avg)
12.22s
Total Cost
$0.646
Rank
#12
Total Output Tokens
64,577
Response Time (avg)
5.87s
Total Cost
$0.309
Recommended model medium

Its score stays close to the best score here (9.4 vs 9.8), while costing about 2.1x less than Gemini 3.7 Flash (high).

Detailed comparison

Metric Gemini 3.7 Flash Gemini 3.7 Flash high Release: 2026-08-14 Gemini 3.7 Flash Gemini 3.7 Flash medium Release: 2026-08-14
Score 9.8 9.4
Rank #6 #12
Reliability 10.0 10.0
Consistency 9.2 9.6
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 95.5% 93.9%
Flaky tests 2 1
Total Runs 66 66
Cost per result 1.615 0.773
Total Cost $0.646 $0.309
Input Price $0.750 / 1M $0.750 / 1M
Output Price $3.750 / 1M $3.750 / 1M
Total Input Tokens 86,712 89,055
Output Tokens 6,017 5,697
Reasoning Tokens 148,829 58,880
Response Time (avg) 12.22s 5.87s
Response Time (max) 91.63s 30.23s
Response Time (total) 268.78s 129.20s
Parameters ~500B total (~20B active) ~500B total (~20B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#6 Gemini 3.7 Flash

high
Cost
$0.039
Time
100.5s
Tokens
20,824 tok

#12 Gemini 3.7 Flash

medium
Cost
$0.014
Time
35.2s
Tokens
7,283 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
Gemini 3.7 Flash 10.0 10.0 100.0% 0 13.55s 8,118 460 26,859
Gemini 3.7 Flash 8.4 7.4 88.9% 1 8.86s 8,118 450 16,777

Quick Compare

Switch Comparison Pair