Navigate
Advertise here

DeepSeek V4 Flash 0731 vs DeepSeek V4 Flash 0423

DeepSeek V4 Flash 0423 leads on average score with 6.3 vs 6.2. DeepSeek V4 Flash 0731 has the lower benchmark cost at $0.053 vs $0.149. DeepSeek V4 Flash 0731 is faster at 27.42s vs 38.64s, with pass rates of 30.4% vs 30.4%.

Last updated at: 2026-10-19

Compared models

Rank
#270
Total Output Tokens
39,789
Response Time (avg)
27.42s
Total Cost
$0.053
Rank
#265
Total Output Tokens
115,591
Response Time (avg)
38.64s
Total Cost
$0.149
Recommended model DeepSeek V4 Flash 0731

Its score stays close to the best score here (6.2 vs 6.3), while costing about 2.8x less than DeepSeek V4 Flash 0423.

Detailed comparison

Metric DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 none Release: 2026-08-01 DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 none Release: 2026-04-24
Score 6.2 6.3
Rank #270 #265
Reliability 10.0 10.0
Consistency 8.7 8.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 30.4% 30.4%
Flaky tests 4 4
Total Runs 69 69
Cost per result 0.826 1.220
Total Cost $0.053 $0.149
Input Price $0.005 / 1M $0.002 / 1M
Output Price $1.280 / 1M $1.280 / 1M
Cache Read Price $0.005 / 1M $0.002 / 1M
Cache Write Price N/A N/A
Total Input Tokens 349,876 403,455
Output Tokens 39,789 100,227
Reasoning Tokens 0 15,364
Response Time (avg) 27.42s 38.64s
Response Time (max) 387.15s 247.27s
Response Time (total) 630.70s 888.69s
Parameters 284B total (13B active) 284B total (13B active)
Availability Closed 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.

#270 DeepSeek V4 Flash 0731

none
Cost
$0.004
Time
198.4s
Tokens
14,316 tok

#265 DeepSeek V4 Flash 0423

none
Cost
$0.004
Time
157.6s
Tokens
11,297 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 Flash 0731 4.3 10.0 0.0% 0 1.72s 7,275 505 0
DeepSeek V4 Flash 0423 4.2 7.4 11.1% 1 17.13s 7,279 498 9,219

Switch Comparison Pair