Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs Z.ai: GLM 5.2

Summary

DeepSeek V4 Pro vs GLM 5.2 benchmark comparison: The average score is effectively tied at 7.2 vs 7.1. DeepSeek V4 Pro has the lower benchmark cost at $0.034 vs $0.076. GLM 5.2 is faster at 6.34s vs 6.41s, with pass rates of 52.4% vs 60.3%.

Recommended model: DeepSeek V4 Pro - It has the best score here (7.2), while costing about 2.3x less than GLM 5.2.

Last updated at: 2026-06-17

Metric DeepSeek V4 Pro DeepSeek V4 Pro none Release: 2026-04-24 GLM 5.2 GLM 5.2 none Release: 2026-06-17
Score 7.2 7.1
Rank #58 #61
Reliability 9.9 9.9
Consistency 8.8 9.6
Tests Correct
Attempt pass rate 52.4% 60.3%
Flaky tests 3 1
Total Runs 63 63
Cost per result 0.333 0.628
Total Cost $0.034 $0.076
Input Price $0.435 / 1M $1.400 / 1M
Output Price $0.870 / 1M $4.400 / 1M
Total Input Tokens 53,558 38,671
Output Tokens 11,424 4,817
Reasoning Tokens 0 0
Response Time (avg) 6.41s 6.34s
Response Time (max) 30.09s 20.69s
Response Time (total) 134.66s 133.19s

Generation showcase

Hamster playing table tennis

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

#58 DeepSeek V4 Pro

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

#61 GLM 5.2

none
Invalid SVG
Cost
$0.033
Time
87.7s
Tokens
7,455 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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.2 6.1 16.7% 2 4.02s 540 1,168 0
GLM 5.2 8.3 10.0 75.0% 0 3.70s 567 313 0
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 5.2 3.7 9.5 0.0% 0 7.55s 7,263 1,958 0
Combined Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 9.5 10.0 100.0% 0 23.74s 27,529 2,235 0
GLM 5.2 10.0 10.0 100.0% 0 20.69s 14,296 1,489 0
Data parsing and extraction Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 4.61s 7,568 200 0
GLM 5.2 10.0 10.0 100.0% 0 7.17s 7,113 204 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.3 10.0 33.3% 0 3.72s 666 24 0
GLM 5.2 5.3 10.0 33.3% 0 6.50s 696 27 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.0 10.0 0.0% 0 2.05s 471 126 0
GLM 5.2 6.1 3.1 66.7% 1 4.42s 480 82 0
Instructions following Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.3 5.8 66.7% 1 4.12s 627 713 0
GLM 5.2 9.8 10.0 100.0% 0 3.84s 642 66 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 3.61s 594 442 0
GLM 5.2 7.7 10.0 66.7% 0 3.31s 618 265 0
Tool Calling Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 10.0 10.0 100.0% 0 7.40s 8,105 328 0
GLM 5.2 10.0 10.0 100.0% 0 15.76s 6,807 400 0
Trivia Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.0 10.0 0.0% 0 5.76s 183 688 0
GLM 5.2 3.0 10.0 0.0% 0 3.41s 189 13 0

Quick Compare

Switch Comparison Pair

DeepSeek V4 PrononevsGemma 4 26B A4BmediumFree AvailableGemma 4 26B A4BmediumFree AvailablevsGLM 5.2noneMiMo-V2-FlashmediumvsGLM 5.2noneStep 3.7 FlashhighvsGLM 5.2noneDeepSeek V4 PrononevsGLM 5V TurbomediumDeepSeek V4 PrononevsMiMo-V2-FlashmediumDeepSeek V4 PrononevsStep 3.7 FlashhighDeepSeek V4 PrononevsGLM 5.1mediumKimi K2.7 CodemediumvsGLM 5.2noneDeepSeek V4 PrononevsKimi K2.7 CodemediumDeepSeek V4 PrononevsGrok 4.20mediumDeepSeek V4 PrononevsGemini 3 Flash Previewlow