Navigate
AI BENCHY
Advertise here

Gemini 3.5 Flash (low) vs Muse Spark 1.2 (medium)

Gemini 3.5 Flash (low) leads on average score with 8.8 vs 8.6. Gemini 3.5 Flash (low) has the lower benchmark cost at $0.449 vs $1.339. Gemini 3.5 Flash (low) is faster at 5.76s vs 19.67s, with pass rates of 84.9% vs 74.2%.

Last updated at: 2026-08-15

Rank
#24
Total Output Tokens
35,195
Response Time (avg)
5.76s
Total Cost
$0.449
Rank
#31
Total Output Tokens
278,664
Response Time (avg)
19.67s
Total Cost
$1.339
Recommended model Gemini 3.5 Flash (low)

It has the best score here (8.8), while costing about 3.0x less than Muse Spark 1.2 (medium).

Detailed comparison

Metric Gemini 3.5 Flash Gemini 3.5 Flash low Release: 2026-05-19 Muse Spark 1.2 Muse Spark 1.2 medium Release: 2026-08-06
Score 8.8 8.6
Rank #24 #31
Reliability 10.0 10.0
Consistency 9.3 8.7
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 84.9% 74.2%
Flaky tests 2 4
Total Runs 66 66
Cost per result 2.492 9.564
Total Cost $0.449 $1.339
Input Price $1.500 / 1M $1.250 / 1M
Output Price $9.000 / 1M $4.250 / 1M
Total Input Tokens 87,826 123,680
Output Tokens 2,239 7,222
Reasoning Tokens 32,956 271,442
Response Time (avg) 5.76s 19.67s
Response Time (max) 53.55s 142.49s
Response Time (total) 126.71s 432.72s
Parameters ~500B total (~20B active) ~1T total (~50B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#24 Gemini 3.5 Flash

low
Cost
$0.068
Time
39.1s
Tokens
7,588 tok

#31 Muse Spark 1.2

medium
Cost
$0.033
Time
21.8s
Tokens
7,846 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 3.5 Flash 7.8 10.0 66.7% 0 6.71s 8,118 458 13,420
Muse Spark 1.2 10.0 10.0 100.0% 0 17.49s 7,275 353 33,215

Quick Compare

Switch Comparison Pair