Navigate
AI BENCHY
Advertise here

Claude Opus 4.8 vs GLM 5.3 (high)

GLM 5.3 (high) leads on average score with 7.3 vs 7.3. GLM 5.3 (high) has the lower benchmark cost at $0.403 vs $1.166. Claude Opus 4.8 is faster at 4.92s vs 27.82s, with pass rates of 63.6% vs 74.2%.

Last updated at: 2026-08-20

Rank
#104
Total Output Tokens
16,797
Response Time (avg)
4.92s
Total Cost
$1.166
Rank
#99
Total Output Tokens
63,667
Response Time (avg)
27.82s
Total Cost
$0.403
Recommended model GLM 5.3 (high)

It has the best score here (7.3), while costing about 2.9x less than Claude Opus 4.8.

Detailed comparison

Metric Claude Opus 4.8 Claude Opus 4.8 none Release: 2026-05-28 GLM 5.3 GLM 5.3 high Release: 2026-08-20
Score 7.3 7.3
Rank #104 #99
Reliability 10.0 10.0
Consistency 9.2 7.5
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 63.6% 74.2%
Flaky tests 2 7
Total Runs 66 66
Cost per result 8.969 3.099
Total Cost $1.166 $0.403
Input Price $5.000 / 1M $1.400 / 1M
Output Price $25.000 / 1M $4.400 / 1M
Total Input Tokens 149,203 87,601
Output Tokens 16,797 6,006
Reasoning Tokens 0 57,661
Response Time (avg) 4.92s 27.82s
Response Time (max) 35.03s 159.91s
Response Time (total) 108.24s 612.06s
Parameters ~5T total (~500B active) 744B total (40B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#104 Claude Opus 4.8

none
Cost
$0.053
Time
22.0s
Tokens
2,253 tok

#99 GLM 5.3

high
Cost
$0.085
Time
362.5s
Tokens
19,310 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
Claude Opus 4.8 5.5 10.0 33.3% 0 3.29s 10,590 1,332 0
GLM 5.3 6.6 5.0 66.7% 2 18.89s 7,317 473 8,190

Quick Compare

Switch Comparison Pair