Claude Opus 4.7 (medium) vs GLM 5.3 FlashX (max)

Compared models

Recommended model GLM 5.3 FlashX (max)

Its score stays close to the best score here (7.9 vs 8.1), while costing about 5.8x less than Claude Opus 4.7 (medium).

Metric	Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16	GLM 5.3 FlashX GLM 5.3 FlashX max Release: 2026-09-21

Metric	Claude Opus 4.7 Claude Opus 4.7 medium Release: 2026-04-16	GLM 5.3 FlashX GLM 5.3 FlashX max Release: 2026-09-21
Score	8.1	7.9
Rank	#88	#97
Reliability	10.0	10.0
Consistency	9.3	8.0
Attempts	69/69	69/69
Tests Correct
Attempt pass rate	81.2%	78.3%
Flaky tests	2	6
Total Runs	69	69
Cost per result	20.200	4.153
Total Cost	$3.636	$0.623
Input Price	$5.000 / 1M	$0.370 / 1M
Output Price	$25.000 / 1M	$1.250 / 1M
Total Input Tokens	437,293	322,894
Output Tokens	29,102	8,010
Reasoning Tokens	28,876	394,755
Response Time (avg)	14.12s	43.97s
Response Time (max)	150.60s	390.70s
Response Time (total)	310.55s	1011.29s
Parameters	~5T total (~500B active)	320B total (18B active)
Availability	Closed	Closed

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

medium

max

Category:

Agentic	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Claude Opus 4.7	5.2	3.2	33.3%	1		150.60s	292,044	4,154	23,834
GLM 5.3 FlashX	6.1	3.1	66.7%	1		104.77s	221,683	1,709	25,322

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 5.3 FlashX	10.0	10.0	100.0%	0		2.65s	639	301	2,210

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 5.3 FlashX	8.2	7.2	88.9%	1		24.61s	7,317	463	36,503

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		43.42s	104,347	15,459	3,928
GLM 5.3 FlashX	8.2	6.9	66.7%	1		45.23s	76,431	3,485	35,762

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 5.3 FlashX	10.0	10.0	100.0%	0		3.38s	7,149	223	2,262

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		1.19s	627	51	0
GLM 5.3 FlashX	3.5	4.4	33.3%	2		224.00s	759	583	279,058

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 5.3 FlashX	10.0	10.0	100.0%	0		5.01s	498	209	1,290

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 5.3 FlashX	9.9	10.0	100.0%	0		2.23s	678	72	1,032

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 5.3 FlashX	8.2	7.7	77.8%	1		3.88s	672	456	2,848

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 5.3 FlashX	10.0	10.0	100.0%	0		9.39s	6,861	231	712

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 5.3 FlashX	3.0	10.0	0.0%	0		22.41s	207	278	7,756

Switch Comparison Pair