Navigate
AI BENCHY
Advertise here

DeepSeek V4 Pro vs GLM 5.3 (low)

The average score is effectively tied at 6.8 vs 6.8. GLM 5.3 (low) has the lower benchmark cost at $0.257 vs $0.351. DeepSeek V4 Pro is faster at 11.71s vs 13.65s, with pass rates of 47.0% vs 65.2%.

Last updated at: 2026-08-20

Rank
#133
Total Output Tokens
35,547
Response Time (avg)
11.71s
Total Cost
$0.351
Rank
#134
Total Output Tokens
24,808
Response Time (avg)
13.65s
Total Cost
$0.257
Recommended model GLM 5.3 (low)

It has the strongest score in this comparison (6.8) and the best overall balance of cost and response time across all 2 models.

Detailed comparison

Metric DeepSeek V4 Pro DeepSeek V4 Pro none Release: 2026-04-24 GLM 5.3 GLM 5.3 low Release: 2026-08-20
Score 6.8 6.8
Rank #133 #134
Reliability 10.0 10.0
Consistency 8.6 8.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 47.0% 65.2%
Flaky tests 4 4
Total Runs 66 66
Cost per result 1.061 2.135
Total Cost $0.351 $0.257
Input Price $1.600 / 1M $1.400 / 1M
Output Price $3.200 / 1M $4.400 / 1M
Total Input Tokens 148,078 104,989
Output Tokens 35,547 8,532
Reasoning Tokens 0 16,276
Response Time (avg) 11.71s 13.65s
Response Time (max) 119.44s 83.60s
Response Time (total) 257.67s 300.22s
Parameters 1.6T total (49B active) 744B total (40B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#133 DeepSeek V4 Pro

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

#134 GLM 5.3

low
Cost
$0.007
Time
28.4s
Tokens
1,599 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
GLM 5.3 6.2 6.9 55.6% 1 21.02s 7,317 368 6,764

Quick Compare

Switch Comparison Pair