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

DeepSeek V4.1 Flash (high) vs DeepSeek V4 Flash 0731 (high)

DeepSeek V4.1 Flash (high) leads on average score with 8.5 vs 8.0. DeepSeek V4 Flash 0731 (high) has the lower benchmark cost at $0.084 vs $0.287. DeepSeek V4.1 Flash (high) is faster at 32.78s vs 114.94s, with pass rates of 74.2% vs 75.8%.

Last updated at: 2026-09-10

Compared models

Rank
#52
Total Output Tokens
452,940
Response Time (avg)
32.78s
Total Cost
$0.287
Rank
#74
Total Output Tokens
513,307
Response Time (avg)
114.94s
Total Cost
$0.084
Recommended model DeepSeek V4.1 Flash (high)

It has the best score here (8.5), while responding about 3.5x faster than DeepSeek V4 Flash 0731 (high).

Detailed comparison

Metric DeepSeek V4.1 Flash DeepSeek V4.1 Flash high Release: 2026-09-10 DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 high Release: 2026-08-01
Score 8.5 8.0
Rank #52 #74
Reliability 9.6 10.0
Consistency 8.9 8.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 74.2% 75.8%
Flaky tests 3 5
Total Runs 66 66
Cost per result 1.912 0.956
Total Cost $0.287 $0.084
Input Price $0.150 / 1M $0.065 / 1M
Output Price $0.600 / 1M $0.180 / 1M
Total Input Tokens 100,111 96,702
Output Tokens 6,642 16,966
Reasoning Tokens 446,298 496,341
Response Time (avg) 32.78s 114.94s
Response Time (max) 205.53s 600.61s
Response Time (total) 721.15s 2528.65s
Parameters 748B total (16B active) 284B total (13B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#52 DeepSeek V4.1 Flash

high
Cost
$0.035
Time
111.0s
Tokens
29,201 tok

#74 DeepSeek V4 Flash 0731

high
No output was saved. The original provider response or failure reason is unavailable.
Cost
$0.000
Time
187.3s
Tokens
19,048 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 10.0 10.0 100.0% 0 49.19s 7,509 376 108,285
DeepSeek V4 Flash 0731 6.3 6.3 55.6% 1 252.67s 7,044 2,160 191,210

Quick Compare

Switch Comparison Pair