Navigate
Advertise here

DeepSeek V4.1 Flash 1017 (max) vs GLM 5.2 (medium)

The average score is effectively tied at 8.2 vs 8.2. DeepSeek V4.1 Flash 1017 (max) has the lower benchmark cost at $0.757 vs $1.007. GLM 5.2 (medium) is faster at 26.88s vs 78.20s, with pass rates of 76.8% vs 81.2%.

Last updated at: 2026-10-19

Compared models

Rank
#100
Total Output Tokens
1,170,181
Response Time (avg)
78.20s
Total Cost
$0.757
Rank
#102
Total Output Tokens
81,020
Response Time (avg)
26.88s
Total Cost
$1.007
Recommended model GLM 5.2 (medium)

It has the best score here (8.2), while responding about 2.9x faster than DeepSeek V4.1 Flash 1017 (max).

Detailed comparison

Metric DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 max Release: 2026-10-18 GLM 5.2 GLM 5.2 medium Release: 2026-06-17
Score 8.2 8.2
Rank #100 #102
Reliability 10.0 9.6
Consistency 8.2 8.1
Attempts 69/69 66/69
Tests Correct
Attempt pass rate 76.8% 81.2%
Flaky tests 5 4
Total Runs 69 66
Cost per result 5.041 2.890
Total Cost $0.757 $1.007
Input Price $0.150 / 1M $0.153 / 1M
Output Price $0.600 / 1M $12.000 / 1M
Cache Read Price $0.003 / 1M $0.150 / 1M
Cache Write Price N/A N/A
Total Input Tokens 360,065 227,164
Output Tokens 7,711 20,029
Reasoning Tokens 1,162,470 60,991
Response Time (avg) 78.20s 26.88s
Response Time (max) 605.14s 102.40s
Response Time (total) 1798.65s 591.34s
Parameters ~748B total (~16B active) 744B total (40B active)
Availability Open source 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.

#100 DeepSeek V4.1 Flash 1017

max
Cost
$0.018
Time
135.0s
Tokens
35,163 tok

#102 GLM 5.2

medium
Cost
$0.041
Time
195.8s
Tokens
9,287 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 1017 5.6 4.2 66.7% 2 199.23s 7,509 111 475,423
GLM 5.2 8.2 7.2 88.9% 1 40.96s 7,317 1,475 17,123

Switch Comparison Pair