AI BENCHY Compare

Anthropic: Claude Opus 4.7 vs Z.ai: GLM 5.2

Summary

Claude Opus 4.7 (medium) leads on average score with 8.7 vs 8.0. GLM 5.2 (high) has the lower benchmark cost at $0.667 vs $0.679. Claude Opus 4.7 (medium) is faster at 4.73s vs 37.09s, with pass rates of 82.5% vs 77.8%.

Recommended modelClaude Opus 4.7 (medium)It has the best score here (8.7), while responding about 7.8x faster than GLM 5.2 (high).

Last updated at: 2026-07-14

Metric	Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16	GLM 5.2 GLM 5.2 high Release: 2026-06-17

Metric	Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16	GLM 5.2 GLM 5.2 high Release: 2026-06-17
Score	8.7	8.0
Rank	#16	#32
Reliability	10.0	9.3
Consistency	9.6	7.6
Tests Correct
Attempt pass rate	82.5%	77.8%
Flaky tests	1	6
Total Runs	63	63
Cost per result	3.991	4.255
Total Cost	$0.679	$0.667
Input Price	$5.000 / 1M	$0.929 / 1M
Output Price	$25.000 / 1M	$2.918 / 1M
Total Input Tokens	65,406	34,993
Output Tokens	11,858	51,575
Reasoning Tokens	2,198	166,065
Response Time (avg)	4.73s	37.09s
Response Time (max)	23.18s	180.69s
Response Time (total)	94.51s	778.91s

Generation showcase

Hamster playing table tennis

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

#16 Claude Opus 4.7

medium

Cost: $0.059
Time: 26.8s
Tokens: 2,475 tok

#32 GLM 5.2

high

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

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	8.3	10.0	75.0%	0		1.85s	894	348	0
GLM 5.2	10.0	10.0	100.0%	0		5.80s	639	406	2,660

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	7.6	7.2	77.8%	1		12.96s	10,635	7,629	1,114
GLM 5.2	6.4	4.4	77.8%	2		73.03s	5,124	2,302	22,546

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		21.45s	24,501	2,369	1,084
GLM 5.2	10.0	10.0	100.0%	0		43.51s	12,696	711	4,267

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		2.37s	10,533	324	0
GLM 5.2	10.0	10.0	100.0%	0		5.81s	7,143	435	1,414

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	7.7	10.0	66.7%	0		1.17s	630	51	0
GLM 5.2	3.5	4.4	33.3%	2		73.97s	551	46,693	90,566

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		2.87s	723	256	0
GLM 5.2	10.0	10.0	100.0%	0		12.90s	498	63	1,743

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		1.57s	939	114	0
GLM 5.2	10.0	10.0	100.0%	0		4.26s	678	151	1,210

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		2.43s	939	370	0
GLM 5.2	6.0	4.6	66.7%	2		33.71s	665	568	22,392

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	10.0	10.0	100.0%	0		4.17s	15,339	373	0
GLM 5.2	10.0	10.0	100.0%	0		9.25s	6,861	246	503

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	3.0	10.0	0.0%	0		2.25s	273	24	0
GLM 5.2	3.0	10.0	0.0%	0		127.82s	138	0	18,764

Quick Compare

Switch Comparison Pair

GPT-5.4 MinimediumvsGLM 5.2high Qwen3.5 Plus 2026-02-15mediumvsGLM 5.2high KAT-Coder-Pro V2.5lowvsGLM 5.2high Nemotron 3 Ultra 550b A55bmediumFree AvailablevsGLM 5.2high Qwen3.7 PlusmediumvsGLM 5.2high Qwen3.5-27BmediumvsGLM 5.2high Claude Sonnet 5mediumvsGLM 5.2high Qwen3.6 PlusmediumvsGLM 5.2high Gemini 2.5 FlashmediumvsGLM 5.2high GPT-5.6 TerramediumvsGLM 5.2high Claude Sonnet 4.6mediumvsGLM 5.2high Grok 4.5lowvsGLM 5.2high