Navigate
AI BENCHY
Advertise here

DeepSeek V4 Pro vs Qwen3.7 Flash (medium)

The average score is effectively tied at 6.9 vs 7.0. Qwen3.7 Flash (medium) has the lower benchmark cost at $0.064 vs $0.096. DeepSeek V4 Pro is faster at 11.55s vs 45.90s, with pass rates of 51.5% vs 65.2%.

Last updated at: 2026-07-28

Rank
#93
Total Output Tokens
35,551
Response Time (avg)
11.55s
Total Cost
$0.096
Rank
#91
Total Output Tokens
462,623
Response Time (avg)
45.90s
Total Cost
$0.064
Recommended model DeepSeek V4 Pro

It has the best score here (6.9), while responding about 4.0x faster than Qwen3.7 Flash (medium).

Detailed comparison

Metric DeepSeek V4 Pro DeepSeek V4 Pro none Release: 2026-04-24 Qwen3.7 Flash Qwen3.7 Flash medium Release: 2026-07-28
Score 6.9 7.0
Rank #93 #91
Reliability 10.0 10.0
Consistency 8.6 7.5
Tests Correct
Attempt pass rate 51.5% 65.2%
Flaky tests 4 7
Total Runs 66 66
Cost per result 0.954 0.636
Total Cost $0.096 $0.064
Input Price $0.435 / 1M $0.030 / 1M
Output Price $0.870 / 1M $0.130 / 1M
Total Input Tokens 148,069 114,468
Output Tokens 35,551 12,786
Reasoning Tokens 0 449,837
Response Time (avg) 11.55s 45.90s
Response Time (max) 119.44s 593.64s
Response Time (total) 254.11s 1009.84s

Hamster playing table tennis

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

#93 DeepSeek V4 Pro

none
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

#91 Qwen3.7 Flash

medium
Invalid SVG
Cost
$0.000
Time
600.0s
Tokens
0 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 Pro 5.6 10.0 33.3% 0 13.38s 7,275 5,500 0
Qwen3.7 Flash 6.2 6.9 55.6% 1 46.78s 7,893 563 61,902

Quick Compare

Switch Comparison Pair