Navigate
Advertise here

Gemini 3.6 Flash (high) vs GPT-6.2 Astra (max)

GPT-6.2 Astra (max) leads on average score with 10.0 vs 9.9. Gemini 3.6 Flash (high) has the lower benchmark cost at $0.900 vs $7.741. Gemini 3.6 Flash (high) is faster at 18.93s vs 47.29s, with pass rates of 98.6% vs 100.0%.

Last updated at: 2026-11-17

Compared models

Rank
#6
Total Output Tokens
192,320
Response Time (avg)
18.93s
Total Cost
$0.900
Rank
#4
Total Output Tokens
156,448
Response Time (avg)
47.29s
Total Cost
$7.741
Recommended model Gemini 3.6 Flash (high)

Its score stays close to the best score here (9.9 vs 10.0), while costing about 8.6x less than GPT-6.2 Astra (max).

Detailed comparison

Metric Gemini 3.6 Flash Gemini 3.6 Flash high Release: 2026-07-21 GPT-6.2 Astra GPT-6.2 Astra max Release: 2026-11-17
Score 9.9 10.0
Rank #6 #4
Reliability 10.0 10.0
Consistency 9.6 10.0
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 98.6% 100.0%
Flaky tests 1 0
Total Runs 69 69
Cost per result 6.872 33.654
Total Cost $0.900 $7.741
Input Price $0.750 / 1M $8.000 / 1M
Output Price $3.750 / 1M $40.000 / 1M
Cache Read Price $0.075 / 1M $0.400 / 1M
Cache Write Price $0.042 / 1M $10.000 / 1M
Total Input Tokens 238,080 185,300
Output Tokens 4,211 5,759
Reasoning Tokens 188,109 150,689
Response Time (avg) 18.93s 47.29s
Response Time (max) 104.15s 683.60s
Response Time (total) 435.48s 1087.57s
Parameters ~500B total (~20B active) ~2T total (~150B active)
Availability 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.

#6 Gemini 3.6 Flash

high
Cost
$0.141
Time
113.7s
Tokens
18,776 tok

#4 GPT-6.2 Astra

max
Cost
$1.128
Time
524.6s
Tokens
28,271 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 3.6 Flash 10.0 10.0 100.0% 0 26.32s 8,128 480 53,005
GPT-6.2 Astra 10.0 10.0 100.0% 0 11.75s 7,302 389 7,312

Switch Comparison Pair