AI BENCHY
Advertise here
#94

GLM 5.2

Z.ai Release: 2026-06-17 Tested on: 2026-07-16 21:17 z-ai/glm-5.2::none
(high) (medium) (none)

Summary

GLM 5.2 scores 6.6 on AI BENCHY and ranks #94. It has 10.0 reliability, a 59.1% pass rate, $0.047 total cost, and 9.34s average response time.

What makes GLM 5.2 unique: It stands out most in Combined, where it ranks #2, while Coding is its weakest area at #13. Its total benchmark cost is unusually low for its score range.

Score

6.6

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$0.047 ↓ -73.0%

Tested at: $0.171

Total Output Tokens

14,340

Total Input Tokens

112,359

Input Price

$0.293 / 1M

Output Price

$0.920 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 59.1%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

9.34s

Response Time (max): 79.65s

Response Time (total): 205.46s

Wrong answer: 8 Did not follow instructions: 1 Invalid tool call: 1

Hamster playing table tennis

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

#94 GLM 5.2

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

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-07-16 21:17 New test added 6.6 10.0 $0.145 ↓ Current run
2026-06-17 10:16 Initial run 7.1 9.9 $0.076 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-17 10:26 $1.400 / 1M $4.400 / 1M
2026-06-29 01:00 $0.950 / 1M $3.000 / 1M
2026-06-30 21:25 $0.930 / 1M $3.000 / 1M
2026-07-08 21:00 $0.420 / 1M $1.320 / 1M
2026-07-09 20:59 $0.540 / 1M $1.760 / 1M
2026-07-10 11:30 $0.770 / 1M $2.420 / 1M
2026-07-17 00:12 $0.919 / 1M $2.887 / 1M
2026-07-18 15:17 $0.293 / 1M $0.920 / 1M

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GLM 5.2nonevsKAT-Coder-Pro V2.5noneGLM 5.2nonevsQwen3.6 35B A3BmediumGLM 5.2nonevsGemma 4 26B A4BmediumFree AvailableGLM 5.2nonevsGemini 3 Flash PreviewnoneGLM 5.2nonevsGemini 3 Flash PreviewmediumGLM 5.2nonevsGemini 3.5 FlashhighGLM 5.2nonevsNemotron 3 UltramediumFree AvailableGLM 5.2nonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 3.7 9.5
Combined 6.9 5.9
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 6.1 3.1
Instructions following 9.8 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models