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

DeepSeek V4 Flash 0731 (medium) vs Step 3.7 Flash (medium)

The average score is effectively tied at 7.8 vs 7.8. DeepSeek V4 Flash 0731 (medium) has the lower benchmark cost at $0.460 vs $0.571. Step 3.7 Flash (medium) is faster at 26.57s vs 94.16s, with pass rates of 72.5% vs 68.1%.

Last updated at: 2026-10-12

Compared models

Rank
#117
Total Output Tokens
358,225
Response Time (avg)
94.16s
Total Cost
$0.460
Rank
#113
Total Output Tokens
440,835
Response Time (avg)
26.57s
Total Cost
$0.571
Recommended model Step 3.7 Flash (medium)

It has the best score here (7.8), while responding about 3.5x faster than DeepSeek V4 Flash 0731 (medium).

Detailed comparison

Metric DeepSeek V4 Flash 0731 DeepSeek V4 Flash 0731 medium Release: 2026-08-01 Step 3.7 Flash Step 3.7 Flash medium Release: 2026-05-29
Score 7.8 7.8
Rank #117 #113
Reliability 10.0 10.0
Consistency 7.2 8.7
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 72.5% 68.1%
Flaky tests 8 4
Total Runs 69 69
Cost per result 1.176 4.392
Total Cost $0.460 $0.571
Input Price $0.005 / 1M $0.200 / 1M
Output Price $1.280 / 1M $1.150 / 1M
Cache Read Price $0.005 / 1M $0.040 / 1M
Cache Write Price N/A N/A
Total Input Tokens 274,189 319,524
Output Tokens 66,689 440,835
Reasoning Tokens 510,525 0
Response Time (avg) 94.16s 26.57s
Response Time (max) 303.26s 152.83s
Response Time (total) 2165.72s 611.09s
Parameters 284B total (13B active) 198B total (11B 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.

#117 DeepSeek V4 Flash 0731

medium
Cost
$0.004
Time
93.3s
Tokens
13,252 tok

#113 Step 3.7 Flash

medium
Cost
$0.006
Time
46.2s
Tokens
4,466 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 6.4 4.4 77.8% 2 198.78s 6,032 4,109 160,154
Step 3.7 Flash 8.8 7.8 88.9% 1 27.42s 7,437 44,797 0

Switch Comparison Pair