Navigate
Advertise here

DeepSeek V4.1 Flash 1017 vs DeepSeek V4.1 Flash

The average score is effectively tied at 5.8 vs 5.8. DeepSeek V4.1 Flash 1017 has the lower benchmark cost at $0.055 vs $0.391. DeepSeek V4.1 Flash 1017 is faster at 3.46s vs 16.63s, with pass rates of 36.2% vs 36.2%.

Last updated at: 2026-10-19

Compared models

Rank
#296
Total Output Tokens
16,806
Response Time (avg)
3.46s
Total Cost
$0.055
Rank
#298
Total Output Tokens
292,779
Response Time (avg)
16.63s
Total Cost
$0.391
Recommended model DeepSeek V4.1 Flash 1017

It has the best score here (5.8), while costing about 7.2x less than DeepSeek V4.1 Flash.

Detailed comparison

Metric DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 none Release: 2026-10-18 DeepSeek V4.1 Flash DeepSeek V4.1 Flash none Release: 2026-09-10
Score 5.8 5.8
Rank #296 #298
Reliability 10.0 9.7
Consistency 9.7 9.1
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 36.2% 36.2%
Flaky tests 1 3
Total Runs 69 69
Cost per result 0.678 2.806
Total Cost $0.055 $0.391
Input Price $0.150 / 1M $0.013 / 1M
Output Price $0.600 / 1M $1.320 / 1M
Cache Read Price $0.003 / 1M $0.013 / 1M
Cache Write Price N/A N/A
Total Input Tokens 293,927 337,756
Output Tokens 16,806 292,779
Reasoning Tokens 0 0
Response Time (avg) 3.46s 16.63s
Response Time (max) 43.95s 247.66s
Response Time (total) 79.48s 382.53s
Parameters ~748B total (~16B active) 748B total (16B active)
Availability Open source Open source

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.

#296 DeepSeek V4.1 Flash 1017

none
Cost
$0.001
Time
7.1s
Tokens
2,012 tok

#298 DeepSeek V4.1 Flash

none
Cost
$0.021
Time
55.4s
Tokens
17,181 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
DeepSeek V4.1 Flash 1017 5.6 9.9 33.3% 0 2.38s 7,284 3,922 0
DeepSeek V4.1 Flash 5.5 10.0 33.3% 0 83.66s 7,284 263,438 0

Switch Comparison Pair