AI BENCHY
Advertise here
#14

GLM 5

Z.ai Release: 2026-02-12 Tested on: 2026-04-22 12:55 z-ai/glm-5::medium
(medium) (none)

Summary

GLM 5 scores 8.4 on AI BENCHY and ranks #14. It has N/A reliability, a 85.2% pass rate, $0.155 total cost, and 23.34s average response time.

What makes GLM 5 unique: Its total benchmark cost is unusually low for its score range.

Score

8.4

Consistency

8.2

Reliability

N/A

Total Cost (Current Price)

$0.155

Total Output Tokens

78,500

Total Input Tokens

0

Input Price

$0.650 / 1M

Output Price

$2.080 / 1M

Tests Correct

Wrong Tests: 5

Attempt pass rate: 85.2%

Flaky tests

4

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

Response Time (avg)

23.34s

Response Time (max): 79.09s

Response Time (total): 233.40s

Wrong answer: 2 Did not follow instructions: 1 No answer: 1 Timed out: 1

Generation showcase

Hamster playing table tennis

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

#14 GLM 5

medium
Cost
$0.005
Time
20.7s
Tokens
2,068 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:07 New test added 8.3 10.0 $0.228 ↓ Compare
2026-05-21 23:44 Re-test 8.2 10.0 $0.237 Compare
2026-04-22 12:55 First recorded run 8.4 N/A $0.155 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-04-22 12:55 · First recorded run8.48.2N/A13/18478,5000$0.15523.34s
2026-05-21 23:44 · Re-test8.28.410.014/204119,8980$0.23733.39s
Difference+0.2-0.2-10-413980-$0.082-10045ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

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 5mediumvsGLM 5.2mediumGLM 5mediumvsGPT-5 MinimediumGLM 5mediumvsClaude Opus 4.7mediumGLM 5mediumvsGPT-5.4mediumGLM 5mediumvsClaude Opus 4.8mediumGLM 5mediumvsSeed-2.0-LitemediumGLM 5mediumvsGemini 3.5 FlashhighGLM 5mediumvsGemini 3 Flash PreviewmediumGLM 5mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableGLM 5mediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 7.1 5.6
Domain specific 3.5 4.4
General Intelligence 6.1 3.1
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0

Compared models