Navigate
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Compared models

Gemini 4 Argon (high) vs Gemini 4 Carbon (high) vs Gemini 4 Hydrogen (high) vs Gemini 3.8 Flash (high) benchmark comparison: Gemini 3.8 Flash (high) leads on Score with 9.9. Gemini 4 Argon (high) leads on Reliability with 10.0. Gemini 4 Argon (high) has the lowest Total Cost at $1.802. Gemini 4 Argon (high) is fastest at 19.03s.

Last updated at: 2026-11-17

Compared models

Rank
#27
Total Output Tokens
132,073
Response Time (avg)
19.03s
Total Cost
$1.802
Rank
#48
Total Output Tokens
513,770
Response Time (avg)
120.04s
Total Cost
$6.107
Rank
#68
Total Output Tokens
212,638
Response Time (avg)
23.79s
Total Cost
$2.019
Rank
#8
Total Output Tokens
446,728
Response Time (avg)
40.60s
Total Cost
$1.927
Recommended model Gemini 4 Argon (high)

Its score stays close to the best score here (9.5 vs 9.9), while costing about 1.9x less than the other models in this comparison.

Detailed comparison

Metric Gemini 4 Argon Gemini 4 Argon high Release: 2026-10-13 Gemini 4 Carbon Gemini 4 Carbon high Release: 2026-11-12 Gemini 4 Hydrogen Gemini 4 Hydrogen high Release: 2026-11-12 Gemini 3.8 Flash Gemini 3.8 Flash high Release: 2026-09-02
Score 9.5 9.2 9.1 9.9
Rank #27 #48 #68 #8
Reliability 10.0 9.2 9.3 10.0
Consistency 9.2 9.2 8.5 9.6
Attempts 69/69 69/69 69/69 69/69
Tests Correct
Attempt pass rate 97.1% 97.1% 94.2% 98.6%
Flaky tests 2 2 4 1
Total Runs 69 69 69 69
Cost per result 8.578 29.080 10.624 8.756
Total Cost $1.802 $6.107 $2.019 $1.927
Input Price $2.000 / 1M $2.000 / 1M $1.500 / 1M $0.750 / 1M
Output Price $10.000 / 1M $10.000 / 1M $7.500 / 1M $3.750 / 1M
Cache Read Price $0.100 / 1M $0.100 / 1M $0.075 / 1M $0.075 / 1M
Cache Write Price $0.188 / 1M $0.188 / 1M $0.084 / 1M $0.042 / 1M
Total Input Tokens 240,264 484,505 282,413 334,568
Output Tokens 5,707 6,098 6,186 11,394
Reasoning Tokens 126,366 507,672 206,452 435,334
Response Time (avg) 19.03s 120.04s 23.79s 40.60s
Response Time (max) 82.53s 443.11s 98.19s 177.08s
Response Time (total) 437.77s 2760.87s 547.07s 933.73s
Parameters ~1.2T total (~20B active) ~1.2T total (~20B active) ~300B total (~15B active) ~500B total (~20B active)
Availability Closed Closed Closed Closed

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#27 Gemini 4 Argon

high
Cost
$0.173
Time
141.5s
Tokens
17,366 tok

#48 Gemini 4 Carbon

high
Reached the allocated time limit (600 seconds) without receiving showcase output.
Cost
$0.000
Time
600.0s
Tokens
0 tok

#68 Gemini 4 Hydrogen

high
Cost
$0.101
Time
85.4s
Tokens
13,562 tok

#8 Gemini 3.8 Flash

high
Cost
$0.077
Time
129.1s
Tokens
20,373 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 4 Argon 10.0 10.0 100.0% 0 15.81s 8,448 489 20,751
Gemini 4 Carbon 10.0 10.0 100.0% 0 119.00s 8,448 495 79,534
Gemini 4 Hydrogen 10.0 10.0 100.0% 0 19.18s 8,448 492 22,526
Gemini 3.8 Flash 10.0 10.0 100.0% 0 29.30s 8,118 462 50,196

Switch Comparison Pair