Navigate
AI BENCHY
Advertise here

DeepSeek: DeepSeek V3.2 vs Z.ai: GLM 5.1

GLM 5.1 (medium) leads on average score with 7.1 vs 7.0. DeepSeek V3.2 (medium) has the lower benchmark cost at $0.078 vs $0.535. GLM 5.1 (medium) is faster at 46.77s vs 68.62s, with pass rates of 65.2% vs 69.7%.

Recommended modelDeepSeek V3.2 (medium)Its score stays close to the best score here (7.0 vs 7.1), while costing about 6.9x less than GLM 5.1 (medium).

Last updated at: 2026-07-17

Metric DeepSeek V3.2 DeepSeek V3.2 medium Release: 2025-12-01 GLM 5.1 GLM 5.1 medium Release: 2026-04-07
Score 7.0 7.1
Rank #73 #71
Reliability 10.0 8.3
Consistency 7.4 8.4
Tests Correct
Attempt pass rate 65.2% 69.7%
Flaky tests 7 4
Total Runs 66 66
Cost per result 0.671 4.202
Total Cost $0.078 $0.535
Input Price $0.269 / 1M $0.966 / 1M
Output Price $0.400 / 1M $3.036 / 1M
Total Input Tokens 101,047 82,623
Output Tokens 11,834 16,089
Reasoning Tokens 117,014 136,463
Response Time (avg) 68.62s 46.77s
Response Time (max) 376.10s 308.75s
Response Time (total) 1509.53s 982.16s

Hamster playing table tennis

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

#73 DeepSeek V3.2

medium
Cost
$0.001
Time
53.6s
Tokens
1,932 tok

#71 GLM 5.1

medium
Invalid SVG
Cost
$0.000
Time
300.0s
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 V3.2 6.0 7.2 55.6% 1 248.68s 5,717 649 52,014
GLM 5.1 4.6 3.7 44.5% 2 109.63s 5,702 4,871 37,826

Quick Compare

Switch Comparison Pair