Compared models

Recommended model GLM 5

It offers the best overall trade-off: a competitive score (5.7), lower cost than the other models in this comparison, and balanced response time.

Detailed comparison

Metric	GLM 5 GLM 5 medium Release: 2026-02-12	GLM 5.1 GLM 5.1 medium Release: 2026-04-07	GLM 5 GLM 5 none Release: 2026-02-12	GLM 5.1 GLM 5.1 none Release: 2026-04-07

Metric	GLM 5 GLM 5 medium Release: 2026-02-12	GLM 5.1 GLM 5.1 medium Release: 2026-04-07	GLM 5 GLM 5 none Release: 2026-02-12	GLM 5.1 GLM 5.1 none Release: 2026-04-07
Score	7.7	7.0	5.7	5.7
Rank	#92	#142	#227	#230
Reliability	10.0	8.1	10.0	10.0
Consistency	8.1	8.4	9.3	8.2
Attempts	63/66	66/66	63/66	66/66
Tests Correct
Attempt pass rate	78.8%	65.2%	42.4%	45.5%
Flaky tests	4	4	1	5
Total Runs	63	66	63	66
Cost per result	1.668	6.923	0.263	2.073
Total Cost	$0.228	$0.727	$0.027	$0.164
Input Price	$0.600 / 1M	$0.966 / 1M	$0.600 / 1M	$0.966 / 1M
Output Price	$1.920 / 1M	$3.036 / 1M	$1.920 / 1M	$3.036 / 1M
Total Input Tokens	35,224	82,592	37,135	124,219
Output Tokens	21,570	16,089	1,989	14,393
Reasoning Tokens	102,996	199,800	0	0
Response Time (avg)	33.54s	58.80s	4.03s	6.74s
Response Time (max)	99.85s	308.75s	11.07s	61.20s
Response Time (total)	435.99s	1234.72s	56.37s	148.20s
Parameters	744B total (40B active)	744B total (40B active)	744B total (40B active)	744B total (40B active)
Availability	Open source	Open source	Open source	Open source

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

medium

medium

Reached the allocated time limit (300 seconds) without receiving showcase output.

none

none

Reached the allocated time limit (300 seconds) without receiving showcase output.

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	10.0	10.0	100.0%	0	23.66s	555	480	7,056
GLM 5.1	10.0	10.0	100.0%	0	8.31s	555	401	5,122
GLM 5	4.8	10.0	25.0%	0	2.37s	510	275	0
GLM 5.1	4.0	6.3	25.0%	2	2.11s	555	305	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	10.0	10.0	100.0%	0	74.30s	7,254	2,997	52,930
GLM 5.1	4.6	3.7	44.5%	2	109.63s	5,702	4,871	37,826
GLM 5	4.0	7.8	11.1%	1	5.12s	7,256	428	0
GLM 5.1	3.9	9.7	0.0%	0	4.96s	7,256	525	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	5.0	5.0	50.0%	0	28.96s	12,804	662	3,242
GLM 5.1	9.8	10.0	100.0%	0	175.93s	66,926	4,761	65,248
GLM 5	1.5	5.0	0.0%	0	4.98s	12,812	406	0
GLM 5.1	2.8	1.8	33.3%	2	46.88s	99,907	12,768	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	7.1	5.6	83.3%	1	8.90s	5,508	567	3,734
GLM 5.1	10.0	10.0	100.0%	0	9.33s	7,107	991	4,552
GLM 5	10.0	10.0	100.0%	0	5.78s	7,107	203	0
GLM 5.1	10.0	10.0	100.0%	0	1.08s	7,107	204	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	3.5	4.4	33.3%	2	0ms	260	13,176	14,137
GLM 5.1	3.0	10.0	0.0%	0	113.95s	458	969	74,651
GLM 5	3.0	10.0	0.0%	0	2.24s	643	19	0
GLM 5.1	5.3	7.2	44.4%	1	2.27s	697	24	0

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	6.1	3.1	66.7%	1	14.69s	477	2,020	2,248
GLM 5.1	10.0	10.0	100.0%	0	20.95s	477	2,875	2,875
GLM 5	10.0	10.0	100.0%	0	3.27s	477	103	0
GLM 5.1	5.0	10.0	0.0%	0	790ms	477	39	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	10.0	10.0	100.0%	0	7.25s	636	1,001	2,129
GLM 5.1	6.4	5.8	66.7%	1	7.47s	634	204	1,617
GLM 5	10.0	10.0	100.0%	0	1.48s	636	61	0
GLM 5.1	9.8	10.0	100.0%	0	1.98s	636	66	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	10.0	10.0	100.0%	0	11.33s	609	33	4,076
GLM 5.1	8.2	7.2	88.9%	1	31.64s	609	935	5,730
GLM 5	7.7	10.0	66.7%	0	1.91s	609	261	0
GLM 5.1	7.7	10.0	66.7%	0	1.45s	609	151	0

Tool Calling	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	10.0	10.0	100.0%	15.93s	6,935	233	994
GLM 5.1	3.0	10.0	0.0%	0ms	0	0	0
GLM 5	10.0	10.0	100.0%	11.07s	6,899	220	0
GLM 5.1	10.0	10.0	100.0%	10.68s	6,789	300	0

Trivia	Score	Consistency	Attempt pass rate	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GLM 5	3.0	10.0	0.0%	67.37s	186	401	12,450
GLM 5.1	3.0	10.0	0.0%	29.40s	124	82	2,179
GLM 5	3.0	10.0	0.0%	3.62s	186	13	0
GLM 5.1	3.0	10.0	0.0%	2.34s	186	11	0

Switch Comparison Pair