Navigate
AI BENCHY
Advertise here

AI BENCHY Compare

DeepSeek: DeepSeek V4 Pro vs Z.ai: GLM 4.7 Flash

Summary

DeepSeek V4 Pro vs GLM 4.7 Flash benchmark comparison: DeepSeek V4 Pro leads on average score with 6.0 vs 5.5. GLM 4.7 Flash has the lower benchmark cost at $0.004 vs $0.079. GLM 4.7 Flash is faster at 2.86s vs 65.21s, with pass rates of 52.4% vs 36.5%.

Recommended model: GLM 4.7 Flash - Its score stays close to the best score here (5.5 vs 6.0), while costing about 23.5x less than DeepSeek V4 Pro.

Last updated at: 2026-06-10

Metric DeepSeek V4 Pro DeepSeek V4 Pro high Release: 2026-04-24 GLM 4.7 Flash GLM 4.7 Flash none Release: 2026-01-19
Score 6.0 5.5
Rank #104 #123
Reliability 9.0 10.0
Consistency 7.6 8.8
Tests Correct
Attempt pass rate 52.4% 36.5%
Flaky tests 6 3
Total Runs 63 63
Cost per result 2.869 0.056
Total Cost $0.079 $0.004
Input Price $0.435 / 1M $0.060 / 1M
Output Price $0.870 / 1M $0.400 / 1M
Total Input Tokens 32,240 38,745
Output Tokens 12,250 2,521
Reasoning Tokens 72,257 0
Response Time (avg) 65.21s 2.86s
Response Time (max) 358.35s 7.05s
Response Time (total) 1304.19s 40.04s

Generation showcase

Hamster playing table tennis

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

#104 DeepSeek V4 Pro

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

#123 GLM 4.7 Flash

none
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

Anti-AI Tricks Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.4 7.9 58.3% 1 16.53s 448 71 3,617
GLM 4.7 Flash 5.2 7.9 41.7% 1 5.51s 555 438 0
Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 3.3 6.4 11.1% 1 118.23s 1,966 111 20,940
GLM 4.7 Flash 4.3 10.0 0.0% 0 2.54s 7,256 650 0
Combined 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 65.02s 14,016 465 5,914
GLM 4.7 Flash 3.0 10.0 0.0% 0 3.22s 14,325 704 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 7.3 5.9 83.3% 1 23.62s 5,633 229 1,710
GLM 4.7 Flash 7.3 5.8 83.3% 1 4.82s 7,107 196 0
Domain specific Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 2.9 7.2 11.1% 1 205.66s 430 10,529 28,089
GLM 4.7 Flash 7.7 10.0 66.7% 0 744ms 687 19 0
General Intelligence Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 6.1 3.1 66.7% 1 25.09s 314 76 1,152
GLM 4.7 Flash 4.0 10.0 0.0% 0 1.59s 477 134 0
Instructions following 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 41.16s 627 205 2,416
GLM 4.7 Flash 6.5 10.0 50.0% 0 888ms 636 62 0
Puzzle Solving Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
DeepSeek V4 Pro 5.9 7.2 55.6% 1 34.84s 544 139 4,019
GLM 4.7 Flash 6.4 10.0 33.3% 0 1.20s 609 97 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 21.33s 8,079 372 593
GLM 4.7 Flash 2.8 1.6 33.3% 1 7.05s 6,907 212 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 39.14s 183 53 3,807
GLM 4.7 Flash 3.0 10.0 0.0% 0 692ms 186 9 0

Quick Compare

Switch Comparison Pair