Navigate
Advertise here

Compared models

DeepSeek V4 Flash 0423 (high) vs DeepSeek V4 Pro 0423 (high) vs GLM 5 (medium) benchmark comparison: DeepSeek V4 Pro 0423 (high) leads on Score with 8.1. DeepSeek V4 Flash 0423 (high) leads on Reliability with 10.0. DeepSeek V4 Flash 0423 (high) has the lowest Total Cost at $0.056. GLM 5 (medium) is fastest at 39.05s.

Last updated at: 2026-10-01

Compared models

Rank
#88
Total Output Tokens
234,594
Response Time (avg)
55.99s
Total Cost
$0.056
Rank
#86
Total Output Tokens
228,663
Response Time (avg)
91.29s
Total Cost
$0.556
Rank
#145
Total Output Tokens
138,257
Response Time (avg)
39.05s
Total Cost
$0.360
Recommended model DeepSeek V4 Flash 0423 (high)

It has the best score here (8.1), while costing about 8.3x less than the other models in this comparison.

Detailed comparison

Metric DeepSeek V4 Flash 0423 DeepSeek V4 Flash 0423 high Release: 2026-04-24 DeepSeek V4 Pro 0423 DeepSeek V4 Pro 0423 high Release: 2026-04-24 GLM 5 GLM 5 medium Release: 2026-02-12
Score 8.1 8.1 7.2
Rank #88 #86 #145
Reliability 10.0 10.0 10.0
Consistency 8.6 7.8 7.9
Attempts 69/69 69/69 66/69
Tests Correct
Attempt pass rate 71.0% 65.2% 76.8%
Flaky tests 4 6 5
Total Runs 69 69 66
Cost per result 0.547 3.717 2.552
Total Cost $0.056 $0.556 $0.360
Input Price $0.079 / 1M $0.783 / 1M $0.600 / 1M
Output Price $0.158 / 1M $1.566 / 1M $1.920 / 1M
Total Input Tokens 298,794 287,061 212,440
Output Tokens 45,873 32,056 22,922
Reasoning Tokens 188,721 196,607 115,335
Response Time (avg) 55.99s 91.29s 39.05s
Response Time (max) 218.13s 416.76s 110.70s
Response Time (total) 1287.87s 2099.56s 546.68s
Parameters 284B total (13B active) 1.6T total (49B active) 744B total (40B active)
Availability Open source Open source Open source

Model generation showcase

Hamster playing table tennis

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

#88 DeepSeek V4 Flash 0423

high
Cost
$0.003
Time
93.1s
Tokens
7,926 tok

#86 DeepSeek V4 Pro 0423

high
Cost
$0.023
Time
257.6s
Tokens
14,870 tok

#145 GLM 5

medium
Cost
$0.005
Time
20.7s
Tokens
2,068 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 0423 7.8 10.0 66.7% 0 50.60s 7,279 395 34,862
DeepSeek V4 Pro 0423 6.3 8.7 33.3% 0 243.00s 5,090 383 84,580
GLM 5 10.0 10.0 100.0% 0 74.30s 7,254 2,997 52,930

Quick Compare

Switch Comparison Pair